所有639 LLMs从智能和成本上进行比较
来自 Artificial Analysis 和其他来源的 2026-09-10 快照中的每个模型，按照运行基准测试所花费的每美元的智能程度进行排名。带星号的行包含智能与成本 Pareto frontier。打开一个模型，看看它的数字，是否仍然是最佳价值，以及正面对决。“开放权重前沿”标记的是没有其他可下载权重模型能超越的可下载权重模型。
- 模型
- 639
- 可下载权重的模型 (open weights)
- 357
- 在帕累托前沿
- 14
- 可下载权重模型前沿（open-weights frontier）
- 6
- 数据快照
- 2026-09-10
今天的Pareto frontier
各个预算下的最佳性价比
每个模型都是同等价格下最智能的选择，其他所有模型都至少被其中一个超越。按价格从低到高排列。
- IBM可下载权重的模型 (open weights)Granite 4.2 3B
- 智能得分 (Intelligence Index)
- 9.10
- 基准测试费用（美元）
- $14.9
- Xiaomi可下载权重的模型 (open weights)MiMo-V2.5
- 智能得分 (Intelligence Index)
- 22.30
- 基准测试费用（美元）
- $42.6
- OpenAIGPT-5.6 Luna (high)
- 智能得分 (Intelligence Index)
- 32.40
- 基准测试费用（美元）
- $108
- OpenAIGPT-5.6 Luna (xhigh)
- 智能得分 (Intelligence Index)
- 34.80
- 基准测试费用（美元）
- $179
- Z AI可下载权重的模型 (open weights)GLM-5.3-Flash
- 智能得分 (Intelligence Index)
- 41.90
- 基准测试费用（美元）
- $280
- OpenAIGPT-5.6 Sol (high)
- 智能得分 (Intelligence Index)
- 42.50
- 基准测试费用（美元）
- $1487
- OpenAIGPT-6 Astra (low)
- 智能得分 (Intelligence Index)
- 46.00
- 基准测试费用（美元）
- $1537
- MetaMuse Spark 1.3 (max)
- 智能得分 (Intelligence Index)
- 48.20
- 基准测试费用（美元）
- $2000
- OpenAIGPT-6 Astra (medium)
- 智能得分 (Intelligence Index)
- 49.70
- 基准测试费用（美元）
- $2434
- OpenAIGPT-6 Astra (high)
- 智能得分 (Intelligence Index)
- 51.00
- 基准测试费用（美元）
- $2917
- OpenAIGPT-6 Astra (xhigh)
- 智能得分 (Intelligence Index)
- 52.50
- 基准测试费用（美元）
- $3803
- OpenAIGPT-6 Astra (max)
- 智能得分 (Intelligence Index)
- 52.80
- 基准测试费用（美元）
- $5324
- AnthropicClaude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
- 智能得分 (Intelligence Index)
- 53.20
- 基准测试费用（美元）
- $9063
- AnthropicClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
- 智能得分 (Intelligence Index)
- 53.40
- 基准测试费用（美元）
- $13129
Last 30 天
最新发布
DeepSeek · 2026-09-10可下载权重的模型 (open weights)DeepSeek V4.1 Flash
- 今天
- 不在前沿
- 发布日期
- 不在前沿
还没有基准数据
OpenBMB · 2026-09-07可下载权重的模型 (open weights)MiniCPM5-2B还没有基准数据
OpenAI · 2026-09-03GPT-6 Astra- 今天
- 最佳性价比前沿
- 发布日期
- 最佳性价比前沿
还没有基准数据
Google · 2026-09-02Gemini 3.8 Flash- 今天
- 不在前沿
- 发布日期
- 不在前沿
- 今天
- 最佳性价比前沿
- 发布日期
- 最佳性价比前沿
- 今天
- 最佳性价比前沿
- 发布日期
- 最佳性价比前沿
639型号，性价比第一
| # | 模型 | 开发者 | 智能得分 (Intelligence Index) | 基准测试费用（美元） | 每美元测试费用的智能得分 | 端到端总耗时（E2E） | 可下载权重 | 发布日期 | 最佳性价比前沿 |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Granite 4.2 3B | IBM | 9.10 | $14.9 | 0.61 | 12.1s | 2026-08-25 | 最佳性价比前沿 | |
| 2 | MiMo-V2.5 | Xiaomi | 22.30 | $42.6 | 0.52 | 55.3s | 2026-04-22 | 最佳性价比前沿 | |
| 3 | DeepSeek V3 (Dec '24) | DeepSeek | 8.50 | $25.4 | 0.34 | - | 2024-12-26 | ||
| 4 | gpt-oss-20b (high) | OpenAI | 9.00 | $29.4 | 0.31 | 14.8s | 2025-08-05 | ||
| 5 | GPT-5.6 Luna (high) | OpenAI | 32.40 | $108 | 0.30 | 23.2s | 2026-07-09 | 最佳性价比前沿 | |
| 6 | Granite 4.2 8B | IBM | 11.80 | $53.1 | 0.22 | 26.1s | 2026-08-25 | ||
| 7 | Mistral Small 3.1 | Mistral | 7.40 | $35.8 | 0.21 | 4.14s | 2025-03-17 | ||
| 8 | Llama 4 Maverick | Meta | 9.30 | $45.5 | 0.20 | 6.53s | 2025-04-05 | ||
| 9 | GPT-5.6 Luna (xhigh) | OpenAI | 34.80 | $179 | 0.19 | 60.1s | 2026-07-09 | 最佳性价比前沿 | |
| 10 | MiMo-V2.5-Pro | Xiaomi | 26.40 | $138 | 0.19 | 73.7s | 2026-04-22 | 开放权重前沿 | |
| 11 | Hy3 | Tencent | 25.80 | $149 | 0.17 | 32.6s | 2026-07-06 | ||
| 12 | GLM-5.3-Flash | Z AI | 41.90 | $280 | 0.15 | 30.5s | 2026-08-26 | 最佳性价比前沿 | |
| 13 | Mistral Small 4 (Reasoning) | Mistral | 11.50 | $78.7 | 0.15 | 16.0s | 2026-03-16 | ||
| 14 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 8.90 | $63.7 | 0.14 | 12.3s | 2025-12-15 | ||
| 15 | Gemini 3.1 Flash-Lite | 16.00 | $119 | 0.13 | 7.51s | 2026-03-03 | |||
| 16 | Nemotron 3.5 Lightning | NVIDIA | 13.60 | $105 | 0.13 | 10.1s | 2026-08-11 | ||
| 17 | DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | 24.60 | $191 | 0.13 | - | 2026-04-24 | ||
| 18 | Muse Glimmer (high) | Meta | 18.10 | $152 | 0.12 | 26.4s | 2026-08-10 | ||
| 19 | DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | 24.80 | $210 | 0.12 | - | 2026-04-24 | ||
| 20 | GPT-5.6 Luna (max) | OpenAI | 37.50 | $320 | 0.12 | 143.2s | 2026-07-09 | ||
| 21 | DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 30.90 | $277 | 0.11 | 84.6s | 2026-04-24 | 开放权重前沿 | |
| 22 | DeepSeek V3 0324 | DeepSeek | 9.70 | $87.2 | 0.11 | - | 2025-03-25 | ||
| 23 | Qwen3.8-Flash-Next | Alibaba | 39.90 | $363 | 0.11 | 49.0s | 2026-08-26 | ||
| 24 | Inkling Small | Thinking Machines | 26.10 | $241 | 0.11 | 21.1s | 2026-07-30 | ||
| 25 | Celeris-1 | Celeris | 6.30 | $60.0 | 0.11 | 0.97s | 2026-07-24 | ||
| 26 | gpt-oss-120b (high) | OpenAI | 12.30 | $122 | 0.10 | 14.2s | 2025-08-05 | ||
| 27 | MiniMax-M2.7 | MiniMax | 23.20 | $236 | 0.10 | 53.6s | 2026-03-18 | ||
| 28 | GPT-5 mini (high) | OpenAI | 17.40 | $189 | 0.09 | 80.6s | 2025-08-07 | ||
| 29 | Gemini 3.5 Flash-Lite | 22.70 | $267 | 0.09 | 9.45s | 2026-07-21 | |||
| 30 | Llama 4 Scout | Meta | 6.50 | $77.6 | 0.08 | 6.69s | 2025-04-05 | ||
| 31 | DeepSeek V4.1 Flash (Reasoning, Max Effort) | DeepSeek | 39.50 | $477 | 0.08 | - | 2026-09-10 | ||
| 32 | GPT-5.6 Terra (low) | OpenAI | 27.90 | $350 | 0.08 | 8.99s | 2026-07-09 | ||
| 33 | DeepSeek V4 Flash Vision (Reasoning, Max Effort) | DeepSeek | 35.00 | $445 | 0.08 | 13.8s | 2026-08-21 | ||
| 34 | Ministral 3 3B | Mistral | 4.80 | $61.3 | 0.08 | 3.58s | 2025-12-02 | ||
| 35 | Grok 4.3 (high) | SpaceXAI | 25.40 | $332 | 0.08 | 25.2s | 2026-04-30 | ||
| 36 | Mercury 2 | Inception | 11.50 | $153 | 0.08 | 4.57s | 2026-02-20 | ||
| 37 | Mistral Large 3 | Mistral | 9.70 | $130 | 0.07 | 7.78s | 2025-12-02 | ||
| 38 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 34.50 | $474 | 0.07 | 14.4s | 2026-07-31 | ||
| 39 | Grok 4.3 (Non-reasoning) | SpaceXAI | 14.50 | $203 | 0.07 | 5.28s | 2026-04-30 | ||
| 40 | GPT-5.6 Terra (medium) | OpenAI | 30.40 | $447 | 0.07 | 9.03s | 2026-07-09 | ||
| 41 | GPT-5.4 nano (xhigh) | OpenAI | 21.20 | $331 | 0.06 | 80.9s | 2026-03-17 | ||
| 42 | MiniMax-M3 | MiniMax | 29.60 | $538 | 0.06 | 30.4s | 2026-06-01 | ||
| 43 | Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 12.70 | $235 | 0.05 | 43.9s | 2025-07-25 | ||
| 44 | GPT-5.6 Sol (low) | OpenAI | 33.80 | $637 | 0.05 | 12.0s | 2026-07-09 | ||
| 45 | Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 9.80 | $188 | 0.05 | 19.2s | 2025-07-30 | ||
| 46 | Solar Pro 3 | Upstage | 7.80 | $159 | 0.05 | 19.1s | 2026-04-06 | ||
| 47 | Grok 4.6 (low) | SpaceXAI | 35.40 | $761 | 0.05 | 16.9s | 2026-08-12 | ||
| 48 | Qwen3.7 Plus | Alibaba | 25.80 | $568 | 0.05 | 46.1s | 2026-06-01 | ||
| 49 | GPT-5.6 Terra (high) | OpenAI | 34.50 | $768 | 0.04 | 10.2s | 2026-07-09 | ||
| 50 | Mistral Small 3.2 | Mistral | 7.00 | $163 | 0.04 | 4.19s | 2025-06-20 | ||
| 51 | GPT-5.6 Sol (medium) | OpenAI | 39.50 | $997 | 0.04 | 17.1s | 2026-07-09 | ||
| 52 | Claude Sonnet 5 (Adaptive Reasoning, Low Effort) | Anthropic | 24.70 | $653 | 0.04 | 10.5s | 2026-06-30 | ||
| 53 | Gemini 3.8 Flash (medium) | 40.00 | $1100 | 0.04 | - | 2026-09-02 | |||
| 54 | Gemini 3.7 Flash (high) | 39.40 | $1084 | 0.04 | 10.3s | 2026-08-13 | |||
| 55 | LongCat 2.0 | LongCat | 19.70 | $545 | 0.04 | 57.0s | 2026-06-29 | ||
| 56 | Claude 4.5 Haiku (Reasoning) | Anthropic | 17.60 | $524 | 0.03 | 26.1s | 2025-10-15 | ||
| 57 | Gemini 3.6 Flash (high) | 34.30 | $1037 | 0.03 | 19.3s | 2026-07-21 | |||
| 58 | Ministral 3 8B | Mistral | 5.50 | $169 | 0.03 | 6.50s | 2025-12-02 | ||
| 59 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 36.30 | $1122 | 0.03 | 37.8s | 2026-08-13 | ||
| 60 | GPT-5.6 Terra (xhigh) | OpenAI | 38.20 | $1187 | 0.03 | 40.1s | 2026-07-09 | ||
| 61 | Qwen3.8 27B (low) | Alibaba | 26.50 | $876 | 0.03 | 54.7s | 2026-08-14 | ||
| 62 | Ring-2.6-1T | InclusionAI | 17.30 | $576 | 0.03 | 24.9s | 2026-05-08 | ||
| 63 | GPT-6 Astra (low) | OpenAI | 46.00 | $1537 | 0.03 | 13.0s | 2026-09-03 | 最佳性价比前沿 | |
| 64 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 23.40 | $801 | 0.03 | 20.0s | 2026-06-04 | ||
| 65 | Qwen3.8 27B (xhigh) | Alibaba | 33.90 | $1170 | 0.03 | 62.9s | 2026-08-14 | ||
| 66 | Muse Spark 1.2 (xhigh) | Meta | 39.80 | $1385 | 0.03 | 26.0s | 2026-08-05 | ||
| 67 | GPT-5.6 Sol (high) | OpenAI | 42.50 | $1487 | 0.03 | 39.6s | 2026-07-09 | 最佳性价比前沿 | |
| 68 | Qwen3.8 27B (medium) | Alibaba | 27.80 | $977 | 0.03 | 54.4s | 2026-08-14 | ||
| 69 | Grok 4.5 (high) | SpaceXAI | 39.10 | $1404 | 0.03 | 23.3s | 2026-07-08 | ||
| 70 | Muse Spark 1.3 (xhigh) | Meta | 45.20 | $1655 | 0.03 | 39.4s | 2026-09-02 | ||
| 71 | Kimi K2.7 Code | Kimi | 26.30 | $993 | 0.03 | 57.9s | 2026-06-12 | ||
| 72 | Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 39.80 | $1561 | 0.03 | 13.6s | 2026-07-24 | ||
| 73 | Gemini 3.8 Flash (high) | 41.20 | $1623 | 0.03 | 13.6s | 2026-09-02 | |||
| 74 | Inkling (xhigh) | Thinking Machines | 25.50 | $1026 | 0.02 | 36.1s | 2026-07-15 | ||
| 75 | DeepSeek R1 (Jan '25) | DeepSeek | 11.40 | $461 | 0.02 | - | 2025-01-20 | ||
| 76 | Qwen3.5 122B A10B (Reasoning) | Alibaba | 16.20 | $661 | 0.02 | 22.0s | 2026-02-24 | ||
| 77 | Muse Spark 1.3 (max) | Meta | 48.20 | $2000 | 0.02 | 38.9s | 2026-09-02 | 最佳性价比前沿 | |
| 78 | Ministral 3 14B | Mistral | 6.00 | $250 | 0.02 | 6.68s | 2025-12-02 | ||
| 79 | Gemini 2.5 Pro | 16.70 | $707 | 0.02 | 26.9s | 2025-06-05 | |||
| 80 | Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 28.40 | $1218 | 0.02 | 10.4s | 2026-06-30 | ||
| 81 | Gemini 3.1 Pro Preview | 30.40 | $1310 | 0.02 | 33.0s | 2026-02-19 | |||
| 82 | GPT-5.5 Instant (June 2026) | OpenAI | 26.80 | $1184 | 0.02 | 21.4s | 2026-06-25 | ||
| 83 | Grok 4.6 (medium) | SpaceXAI | 43.00 | $1937 | 0.02 | 42.8s | 2026-08-12 | ||
| 84 | Qwen3 Coder Next | Alibaba | 10.10 | $476 | 0.02 | 5.99s | 2026-02-03 | ||
| 85 | GPT-5.6 Sol (xhigh) | OpenAI | 44.10 | $2082 | 0.02 | 69.0s | 2026-07-09 | ||
| 86 | Trinity Large Thinking | Arcee AI | 10.90 | $518 | 0.02 | 9.00s | 2026-04-01 | ||
| 87 | Qwen3.6 35B A3B (Reasoning) | Alibaba | 18.80 | $896 | 0.02 | 48.0s | 2026-04-16 | ||
| 88 | GPT-6 Astra (medium) | OpenAI | 49.70 | $2434 | 0.02 | 17.2s | 2026-09-03 | 最佳性价比前沿 | |
| 89 | Qwen3.5 397B A17B (Reasoning) | Alibaba | 19.10 | $941 | 0.02 | 49.1s | 2026-02-16 | ||
| 90 | Muse Spark 1.1 (xhigh) | Meta | 34.30 | $1737 | 0.02 | - | 2026-07-09 | ||
| 91 | Qwen3.6 27B (Reasoning) | Alibaba | 21.90 | $1145 | 0.02 | 114.5s | 2026-04-22 | ||
| 92 | Grok 4.6 (high) | SpaceXAI | 44.40 | $2352 | 0.02 | 50.1s | 2026-08-12 | ||
| 93 | GLM-5.1 (Reasoning) | Z AI | 26.40 | $1418 | 0.02 | 67.8s | 2026-04-07 | ||
| 94 | GLM-5.3 (max) | Z AI | 44.90 | $2503 | 0.02 | 46.0s | 2026-08-18 | 开放权重前沿 | |
| 95 | GPT-6 Astra (high) | OpenAI | 51.00 | $2917 | 0.02 | 95.1s | 2026-09-03 | 最佳性价比前沿 | |
| 96 | GPT-5.4 mini (xhigh) | OpenAI | 24.60 | $1438 | 0.02 | 141.8s | 2026-03-17 | ||
| 97 | GPT-5.6 Terra (max) | OpenAI | 42.30 | $2501 | 0.02 | 197.0s | 2026-07-09 | ||
| 98 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 45.10 | $2732 | 0.02 | 18.5s | 2026-07-24 | ||
| 99 | GPT-5.5 (medium) | OpenAI | 34.20 | $2095 | 0.02 | 14.6s | 2026-04-23 | ||
| 100 | Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 13.60 | $859 | 0.02 | 21.8s | 2026-03-11 | ||
| 101 | Grok 4.6 (xhigh) | SpaceXAI | 44.30 | $2830 | 0.02 | 50.5s | 2026-08-12 | ||
| 102 | Claude Sonnet 5 (Adaptive Reasoning, High Effort) | Anthropic | 32.00 | $2086 | 0.02 | 18.4s | 2026-06-30 | ||
| 103 | Qwen3.8 2.4T A95B | Alibaba | 40.00 | $2632 | 0.02 | 67.9s | 2026-08-12 | ||
| 104 | Gemini 3.5 Flash (high) | 33.00 | $2172 | 0.02 | 19.8s | 2026-05-19 | |||
| 105 | Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) | Anthropic | 47.00 | $3158 | 0.01 | 18.1s | 2026-09-01 | ||
| 106 | Claude 4.5 Sonnet (Reasoning) | Anthropic | 21.20 | $1501 | 0.01 | 28.4s | 2025-09-29 | ||
| 107 | GPT-6 Astra (xhigh) | OpenAI | 52.50 | $3803 | 0.01 | 218.4s | 2026-09-03 | 最佳性价比前沿 | |
| 108 | GPT-5.6 Sol (max) | OpenAI | 47.10 | $3465 | 0.01 | 165.3s | 2026-07-09 | ||
| 109 | Qwen3.7 Max | Alibaba | 29.90 | $2277 | 0.01 | 19.5s | 2026-05-19 | ||
| 110 | Mistral Medium 3.5 | Mistral | 14.90 | $1160 | 0.01 | 20.6s | 2026-04-29 | ||
| 111 | Qwen3.8 Max | Alibaba | 40.30 | $3172 | 0.01 | 68.5s | 2026-08-03 | ||
| 112 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | Anthropic | 49.10 | $3983 | 0.01 | 23.4s | 2026-09-01 | ||
| 113 | Kimi K3 (max) | Kimi | 43.80 | $3658 | 0.01 | 69.5s | 2026-07-16 | ||
| 114 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 48.20 | $4332 | 0.01 | 32.8s | 2026-07-24 | ||
| 115 | GPT-5.5 (high) | OpenAI | 37.30 | $3411 | 0.01 | 18.1s | 2026-04-23 | ||
| 116 | Quasar 438B (max, based on GLM-5.2) | Multiverse Computing | 27.10 | $2504 | 0.01 | 14.9s | 2026-08-10 | ||
| 117 | GPT-6 Astra (max) | OpenAI | 52.80 | $5324 | 0.01 | 346.5s | 2026-09-03 | 最佳性价比前沿 | |
| 118 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic | 51.20 | $5242 | 0.01 | 33.1s | 2026-09-01 | ||
| 119 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 49.70 | $5868 | 0.01 | 40.9s | 2026-07-24 | ||
| 120 | GPT-5.5 (xhigh) | OpenAI | 38.60 | $5294 | 0.01 | 64.5s | 2026-04-23 | ||
| 121 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 50.70 | $7275 | 0.01 | 102.8s | 2026-07-24 | ||
| 122 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 30.50 | $4925 | 0.01 | 138.4s | 2026-02-17 | ||
| 123 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 42.00 | $6874 | 0.01 | 38.2s | 2026-05-28 | ||
| 124 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic | 53.20 | $9063 | 0.01 | 134.6s | 2026-09-01 | 最佳性价比前沿 | |
| 125 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 38.40 | $6998 | 0.01 | 219.2s | 2026-06-30 | ||
| 126 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 49.70 | $11161 | 0.00 | 105.2s | 2026-06-09 | ||
| 127 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | Anthropic | 53.40 | $13129 | 0.00 | 307.3s | 2026-09-01 | 最佳性价比前沿 | |
| 128 | A.X-K2 | SK Telecom | 22.70 | - | - | - | 2026-08-12 | ||
| 129 | Agnes 2.5 Pro Alpha | Sapiens AI | 26.80 | - | - | 17.6s | 2026-07-24 | ||
| 130 | Agnes 2.5 Pro Beta | Sapiens AI | 35.20 | - | - | - | 2026-08-26 | ||
| 131 | Apertus 70B Instruct | Swiss AI Initiative | 5.10 | - | - | - | 2025-09-02 | ||
| 132 | Apertus 8B Instruct | Swiss AI Initiative | 4.80 | - | - | - | 2025-09-02 | ||
| 133 | Apodex 1.1 | Apodex | 30.40 | - | - | - | 2026-08-30 | ||
| 134 | Apriel-v1.5-15B-Thinker | ServiceNow | 13.80 | - | - | - | 2025-09-30 | ||
| 135 | Apriel-v1.6-15B-Thinker | ServiceNow | 13.40 | - | - | - | 2025-11-25 | ||
| 136 | Arctic Instruct | Snowflake | 5.40 | - | - | - | 2024-04-24 | ||
| 137 | Claude 2.0 | Anthropic | 5.50 | - | - | - | 2023-07-11 | ||
| 138 | Claude 2.1 | Anthropic | 5.60 | - | - | - | 2023-11-21 | ||
| 139 | Claude 3 Haiku | Anthropic | 5.60 | - | - | - | 2024-03-04 | ||
| 140 | Claude 3 Opus | Anthropic | 8.70 | - | - | - | 2024-03-04 | ||
| 141 | Claude 3 Sonnet | Anthropic | 5.90 | - | - | - | 2024-03-04 | ||
| 142 | Claude 3.5 Haiku | Anthropic | 8.90 | - | - | - | 2024-10-22 | ||
| 143 | Claude 3.5 Sonnet (June '24) | Anthropic | 7.20 | - | - | - | 2024-06-21 | ||
| 144 | Claude 3.5 Sonnet (Oct '24) | Anthropic | 7.90 | - | - | - | 2024-10-22 | ||
| 145 | Claude 3.7 Sonnet (Non-reasoning) | Anthropic | 15.30 | - | - | - | 2025-02-24 | ||
| 146 | Claude 3.7 Sonnet (Reasoning) | Anthropic | 17.70 | - | - | - | 2025-02-24 | ||
| 147 | Claude 4 Opus (Non-reasoning) | Anthropic | 16.60 | - | - | - | 2025-05-22 | ||
| 148 | Claude 4 Opus (Reasoning) | Anthropic | 20.60 | - | - | - | 2025-05-22 | ||
| 149 | Claude 4 Sonnet (Non-reasoning) | Anthropic | 16.60 | - | - | - | 2025-05-22 | ||
| 150 | Claude 4 Sonnet (Reasoning) | Anthropic | 18.90 | - | - | - | 2025-05-22 | ||
| 151 | Claude 4.1 Opus (Non-reasoning) | Anthropic | 18.60 | - | - | - | 2025-08-05 | ||
| 152 | Claude 4.1 Opus (Reasoning) | Anthropic | 22.80 | - | - | - | 2025-08-05 | ||
| 153 | Claude 4.5 Haiku (Non-reasoning) | Anthropic | 15.40 | - | - | 7.22s | 2025-10-15 | ||
| 154 | Claude 4.5 Sonnet (Non-reasoning) | Anthropic | 19.30 | - | - | 14.7s | 2025-09-29 | ||
| 155 | Claude Instant | Anthropic | 5.00 | - | - | - | 2023-03-14 | ||
| 156 | Claude Opus 4.5 (Non-reasoning) | Anthropic | 23.70 | - | - | 12.8s | 2025-11-24 | ||
| 157 | Claude Opus 4.5 (Reasoning) | Anthropic | 29.10 | - | - | 28.5s | 2025-11-24 | ||
| 158 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 31.90 | - | - | 37.5s | 2026-02-05 | ||
| 159 | Claude Opus 4.6 (Non-reasoning, High Effort) | Anthropic | 26.40 | - | - | 16.1s | 2026-02-05 | ||
| 160 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 40.70 | - | - | 33.3s | 2026-04-16 | ||
| 161 | Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic | 30.90 | - | - | 13.2s | 2026-04-16 | ||
| 162 | Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic | 24.70 | - | - | 14.1s | 2026-02-17 | ||
| 163 | Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 23.30 | - | - | 13.9s | 2026-02-17 | ||
| 164 | Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | - | - | - | 33.2s | 2026-06-30 | ||
| 165 | Claude Sonnet 5 (Non-reasoning, High Effort) | Anthropic | 28.90 | - | - | 10.0s | 2026-06-30 | ||
| 166 | Cogito v2.1 (Reasoning) | Deep Cogito | - | - | - | - | 2025-11-18 | ||
| 167 | Command A | Cohere | 7.00 | - | - | 9.08s | 2025-03-13 | ||
| 168 | Command-R (Mar '24) | Cohere | 5.00 | - | - | - | 2024-03-12 | ||
| 169 | Command-R+ (Apr '24) | Cohere | 5.30 | - | - | - | 2024-04-04 | ||
| 170 | DBRX Instruct | Databricks | 5.30 | - | - | - | 2024-03-27 | ||
| 171 | DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research | 5.10 | - | - | - | 2025-02-13 | ||
| 172 | DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 6.10 | - | - | - | 2025-03-13 | ||
| 173 | DeepSeek Coder V2 Lite Instruct | DeepSeek | 5.30 | - | - | - | 2024-06-17 | ||
| 174 | DeepSeek LLM 67B Chat (V1) | DeepSeek | 5.30 | - | - | - | 2023-11-29 | ||
| 175 | DeepSeek R1 0528 (May '25) | DeepSeek | 13.10 | - | - | - | 2025-05-28 | ||
| 176 | DeepSeek R1 0528 Qwen3 8B | DeepSeek | 8.10 | - | - | - | 2025-05-29 | ||
| 177 | DeepSeek R1 Distill Llama 70B | DeepSeek | 7.90 | - | - | 121.1s | 2025-01-20 | ||
| 178 | DeepSeek R1 Distill Llama 8B | DeepSeek | 6.50 | - | - | - | 2025-01-20 | ||
| 179 | DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 5.50 | - | - | - | 2025-01-20 | ||
| 180 | DeepSeek R1 Distill Qwen 14B | DeepSeek | 7.80 | - | - | - | 2025-01-20 | ||
| 181 | DeepSeek R1 Distill Qwen 32B | DeepSeek | 8.40 | - | - | - | 2025-01-20 | ||
| 182 | DeepSeek V3.1 (Non-reasoning) | DeepSeek | 13.70 | - | - | - | 2025-08-21 | ||
| 183 | DeepSeek V3.1 (Reasoning) | DeepSeek | 13.50 | - | - | - | 2025-08-21 | ||
| 184 | DeepSeek V3.1 Terminus (Non-reasoning) | DeepSeek | 13.90 | - | - | - | 2025-09-22 | ||
| 185 | DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 15.40 | - | - | - | 2025-09-22 | ||
| 186 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | 16.00 | - | - | - | 2025-12-01 | ||
| 187 | DeepSeek V3.2 (Reasoning) | DeepSeek | 21.50 | - | - | - | 2025-12-01 | ||
| 188 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | 13.90 | - | - | - | 2025-09-29 | ||
| 189 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | 16.60 | - | - | - | 2025-09-29 | ||
| 190 | DeepSeek V3.2 Speciale | DeepSeek | 14.50 | - | - | - | 2025-12-01 | ||
| 191 | DeepSeek V4 Flash (Non-reasoning) | DeepSeek | 18.90 | - | - | - | 2026-04-24 | ||
| 192 | DeepSeek V4 Pro (Non-reasoning) | DeepSeek | 20.80 | - | - | 9.51s | 2026-04-24 | ||
| 193 | DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 30.10 | - | - | 40.0s | 2026-04-24 | ||
| 194 | DeepSeek-Coder-V2 | DeepSeek | 6.00 | - | - | - | 2024-06-17 | ||
| 195 | DeepSeek-V2-Chat | DeepSeek | 5.50 | - | - | - | 2024-05-06 | ||
| 196 | DeepSeek-V2.5 | DeepSeek | 6.60 | - | - | - | 2024-09-06 | ||
| 197 | DeepSeek-V2.5 (Dec '24) | DeepSeek | 6.60 | - | - | - | 2024-12-10 | ||
| 198 | Devstral Medium | Mistral | 9.00 | - | - | - | 2025-07-10 | ||
| 199 | Devstral Small (Jul '25) | Mistral | 7.60 | - | - | - | 2025-07-10 | ||
| 200 | Devstral Small (May '25) | Mistral | 8.70 | - | - | - | 2025-05-21 | ||
| 201 | DiffusionGemma 26B A4B | 9.50 | - | - | - | 2026-06-10 | |||
| 202 | Doubao Seed Code | ByteDance Seed | 16.90 | - | - | - | 2025-11-11 | ||
| 203 | ERNIE 4.5 300B A47B | Baidu | 7.50 | - | - | - | 2025-06-30 | ||
| 204 | ERNIE 5.0 Thinking Preview | Baidu | 14.30 | - | - | - | 2025-11-13 | ||
| 205 | Exaone 4.0 1.2B (Non-reasoning) | LG AI Research | 5.20 | - | - | - | 2025-07-15 | ||
| 206 | Exaone 4.0 1.2B (Reasoning) | LG AI Research | 5.30 | - | - | - | 2025-07-15 | ||
| 207 | EXAONE 4.0 32B (Non-reasoning) | LG AI Research | 6.30 | - | - | - | 2025-07-15 | ||
| 208 | EXAONE 4.0 32B (Reasoning) | LG AI Research | 8.20 | - | - | - | 2025-07-15 | ||
| 209 | EXAONE 4.5 33B | LG AI Research | 13.20 | - | - | - | 2026-04-09 | ||
| 210 | EXAONE 4.5 33B (Non-reasoning) | LG AI Research | - | - | - | - | 2026-04-09 | ||
| 211 | Falcon-H1R-7B | TII UAE | 7.80 | - | - | - | 2026-01-04 | ||
| 212 | G9v3-39A5B | AI9Stars | 21.80 | - | - | - | 2026-08-20 | ||
| 213 | G9v3-3B | AI9Stars | 10.80 | - | - | - | 2026-07-23 | ||
| 214 | Gemini 1.0 Pro | 5.30 | - | - | - | 2023-12-06 | |||
| 215 | Gemini 1.0 Ultra | 5.80 | - | - | - | 2023-12-06 | |||
| 216 | Gemini 1.5 Flash (May '24) | 5.90 | - | - | - | 2024-05-14 | |||
| 217 | Gemini 1.5 Flash (Sep '24) | 7.10 | - | - | - | 2024-09-24 | |||
| 218 | Gemini 1.5 Flash-8B | 6.20 | - | - | - | 2024-10-03 | |||
| 219 | Gemini 1.5 Pro (May '24) | 6.40 | - | - | - | 2024-05-15 | |||
| 220 | Gemini 1.5 Pro (Sep '24) | 7.90 | - | - | - | 2024-09-24 | |||
| 221 | Gemini 2.0 Flash (experimental) | 8.20 | - | - | - | 2024-12-11 | |||
| 222 | Gemini 2.0 Flash (Feb '25) | 8.90 | - | - | - | 2025-02-05 | |||
| 223 | Gemini 2.0 Flash Thinking Experimental (Dec '24) | 6.60 | - | - | - | 2024-12-19 | |||
| 224 | Gemini 2.0 Flash Thinking Experimental (Jan '25) | 9.40 | - | - | - | 2025-01-21 | |||
| 225 | Gemini 2.0 Flash-Lite (Feb '25) | 7.40 | - | - | - | 2025-02-25 | |||
| 226 | Gemini 2.0 Flash-Lite (Preview) | 7.30 | - | - | - | 2025-02-05 | |||
| 227 | Gemini 2.0 Pro Experimental (Feb '25) | 8.70 | - | - | - | 2025-02-05 | |||
| 228 | Gemini 2.5 Flash (Non-reasoning) | 9.90 | - | - | 3.12s | 2025-05-20 | |||
| 229 | Gemini 2.5 Flash (Reasoning) | 13.10 | - | - | 18.6s | 2025-05-20 | |||
| 230 | Gemini 2.5 Flash Preview (Non-reasoning) | 8.70 | - | - | - | 2025-04-17 | |||
| 231 | Gemini 2.5 Flash Preview (Reasoning) | 11.70 | - | - | - | 2025-04-17 | |||
| 232 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 12.40 | - | - | - | 2025-09-25 | |||
| 233 | Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 15.50 | - | - | - | 2025-09-25 | |||
| 234 | Gemini 2.5 Flash-Lite (Non-reasoning) | 6.70 | - | - | 2.10s | 2025-06-17 | |||
| 235 | Gemini 2.5 Flash-Lite (Reasoning) | 8.50 | - | - | 22.5s | 2025-06-17 | |||
| 236 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 9.30 | - | - | - | 2025-09-25 | |||
| 237 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 10.40 | - | - | - | 2025-09-08 | |||
| 238 | Gemini 2.5 Pro Preview (Mar' 25) | 15.00 | - | - | - | 2025-03-25 | |||
| 239 | Gemini 2.5 Pro Preview (May' 25) | 14.50 | - | - | - | 2025-05-06 | |||
| 240 | Gemini 3 Deep Think | - | - | - | - | 2026-02-05 | |||
| 241 | Gemini 3 Flash Preview (Non-reasoning) | 17.90 | - | - | 3.45s | 2025-12-17 | |||
| 242 | Gemini 3 Flash Preview (Reasoning) | 26.30 | - | - | 8.84s | 2025-12-17 | |||
| 243 | Gemini 3 Pro Preview (high) | 28.00 | - | - | - | 2025-11-18 | |||
| 244 | Gemini 3 Pro Preview (low) | 22.30 | - | - | - | 2025-11-18 | |||
| 245 | Gemini 3.5 Flash (medium) | 33.60 | - | - | 17.8s | 2026-05-19 | |||
| 246 | Gemini 3.5 Flash (minimal) | 23.80 | - | - | 3.41s | 2026-05-19 | |||
| 247 | Gemini 3.7 Flash (low) | 36.90 | - | - | 2.41s | 2026-08-13 | |||
| 248 | Gemini 3.7 Flash (medium) | 39.60 | - | - | 6.45s | 2026-08-13 | |||
| 249 | Gemini 3.8 Flash (low) | 33.80 | - | - | - | 2026-09-02 | |||
| 250 | Gemma 3 1B Instruct | 4.80 | - | - | - | 2025-03-13 | |||
| 251 | Gemma 3 270M | 5.10 | - | - | - | 2025-08-14 | |||
| 252 | Gemma 3 4B Instruct | 4.80 | - | - | - | 2025-03-12 | |||
| 253 | Gemma 3n E2B Instruct | 4.80 | - | - | - | 2025-06-26 | |||
| 254 | Gemma 3n E4B Instruct | 4.80 | - | - | - | 2025-06-26 | |||
| 255 | Gemma 3n E4B Instruct Preview (May '25) | 5.80 | - | - | - | 2025-05-20 | |||
| 256 | Gemma 4 12B (Non-reasoning) | 9.40 | - | - | 7.43s | 2026-06-03 | |||
| 257 | Gemma 4 12B (Reasoning) | 14.20 | - | - | 26.1s | 2026-06-03 | |||
| 258 | Gemma 4 26B A4B (Non-reasoning) | 13.10 | - | - | 7.90s | 2026-04-02 | |||
| 259 | Gemma 4 26B A4B (Reasoning) | 16.70 | - | - | - | 2026-04-02 | |||
| 260 | Gemma 4 31B (Non-reasoning) | 13.90 | - | - | 11.0s | 2026-04-02 | |||
| 261 | Gemma 4 E2B (Non-reasoning) | 6.50 | - | - | - | 2026-04-02 | |||
| 262 | Gemma 4 E2B (Reasoning) | 7.80 | - | - | - | 2026-04-02 | |||
| 263 | Gemma 4 E4B (Non-reasoning) | 7.50 | - | - | 12.3s | 2026-04-03 | |||
| 264 | Gemma 4 E4B (Reasoning) | 8.90 | - | - | 59.1s | 2026-04-03 | |||
| 265 | GLM 5V Turbo (Reasoning) | Z AI | 23.50 | - | - | - | 2026-04-01 | ||
| 266 | GLM-4.5 (Reasoning) | Z AI | 12.80 | - | - | - | 2025-07-28 | ||
| 267 | GLM-4.5-Air | Z AI | 11.10 | - | - | 51.1s | 2025-07-28 | ||
| 268 | GLM-4.5V (Non-reasoning) | Z AI | 6.70 | - | - | 18.3s | 2025-08-11 | ||
| 269 | GLM-4.5V (Reasoning) | Z AI | 7.60 | - | - | 77.9s | 2025-08-11 | ||
| 270 | GLM-4.6 (Non-reasoning) | Z AI | 14.90 | - | - | 15.4s | 2025-09-30 | ||
| 271 | GLM-4.6 (Reasoning) | Z AI | 18.50 | - | - | 88.8s | 2025-09-30 | ||
| 272 | GLM-4.6V (Non-reasoning) | Z AI | 8.40 | - | - | 12.2s | 2025-12-08 | ||
| 273 | GLM-4.6V (Reasoning) | Z AI | 11.20 | - | - | 46.3s | 2025-12-08 | ||
| 274 | GLM-4.7 (Non-reasoning) | Z AI | 17.40 | - | - | 7.33s | 2025-12-22 | ||
| 275 | GLM-4.7 (Reasoning) | Z AI | 22.20 | - | - | 35.5s | 2025-12-22 | ||
| 276 | GLM-4.7-Flash (Non-reasoning) | Z AI | 10.60 | - | - | 6.54s | 2026-01-19 | ||
| 277 | GLM-4.7-Flash (Reasoning) | Z AI | 14.90 | - | - | 27.1s | 2026-01-19 | ||
| 278 | GLM-5 (Non-reasoning) | Z AI | 21.80 | - | - | 10.2s | 2026-02-11 | ||
| 279 | GLM-5 (Reasoning) | Z AI | 27.90 | - | - | 56.3s | 2026-02-11 | ||
| 280 | GLM-5-Turbo | Z AI | 26.60 | - | - | - | 2026-03-15 | ||
| 281 | GLM-5.1 (Non-reasoning) | Z AI | 24.20 | - | - | 14.7s | 2026-04-07 | ||
| 282 | GLM-5.2 (max) | Z AI | 38.60 | - | - | 42.0s | 2026-06-16 | ||
| 283 | GLM-5.2 (Non-reasoning) | Z AI | 22.40 | - | - | 6.56s | 2026-06-16 | ||
| 284 | GPT-3.5 Turbo | OpenAI | 5.50 | - | - | - | 2022-11-30 | ||
| 285 | GPT-3.5 Turbo (0613) | OpenAI | - | - | - | - | 2023-06-13 | ||
| 286 | GPT-4 | OpenAI | 6.70 | - | - | - | 2023-03-14 | ||
| 287 | GPT-4 Turbo | OpenAI | 7.00 | - | - | 19.5s | 2023-11-06 | ||
| 288 | GPT-4.1 | OpenAI | 12.70 | - | - | 4.13s | 2025-04-14 | ||
| 289 | GPT-4.1 mini | OpenAI | 10.20 | - | - | 5.29s | 2025-04-14 | ||
| 290 | GPT-4.1 nano | OpenAI | 7.80 | - | - | 5.44s | 2025-04-14 | ||
| 291 | GPT-4.5 (Preview) | OpenAI | 9.60 | - | - | - | 2025-02-27 | ||
| 292 | GPT-4o (Aug '24) | OpenAI | 7.70 | - | - | 6.86s | 2024-08-06 | ||
| 293 | GPT-4o (ChatGPT) | OpenAI | 7.20 | - | - | - | 2025-02-15 | ||
| 294 | GPT-4o (March 2025, chatgpt-4o-latest) | OpenAI | 9.00 | - | - | - | 2025-03-27 | ||
| 295 | GPT-4o (May '24) | OpenAI | 7.30 | - | - | 7.34s | 2024-05-13 | ||
| 296 | GPT-4o (Nov '24) | OpenAI | 8.40 | - | - | 5.10s | 2024-11-20 | ||
| 297 | GPT-4o mini | OpenAI | 6.70 | - | - | 4.15s | 2024-07-18 | ||
| 298 | GPT-4o mini Realtime (Dec '24) | OpenAI | - | - | - | - | 2024-12-17 | ||
| 299 | GPT-4o Realtime (Dec '24) | OpenAI | - | - | - | - | 2024-12-17 | ||
| 300 | GPT-5 (ChatGPT) | OpenAI | 10.40 | - | - | - | 2025-08-07 | ||
| 301 | GPT-5 (high) | OpenAI | 23.00 | - | - | 84.3s | 2025-08-07 | ||
| 302 | GPT-5 (low) | OpenAI | 20.80 | - | - | 16.8s | 2025-08-07 | ||
| 303 | GPT-5 (medium) | OpenAI | 22.90 | - | - | 49.5s | 2025-08-07 | ||
| 304 | GPT-5 (minimal) | OpenAI | 11.40 | - | - | 8.50s | 2025-08-07 | ||
| 305 | GPT-5 Codex (high) | OpenAI | 24.90 | - | - | - | 2025-09-23 | ||
| 306 | GPT-5 mini (medium) | OpenAI | 20.60 | - | - | 17.9s | 2025-08-07 | ||
| 307 | GPT-5 mini (minimal) | OpenAI | 9.90 | - | - | 5.95s | 2025-08-07 | ||
| 308 | GPT-5 nano (high) | OpenAI | 13.00 | - | - | 102.1s | 2025-08-07 | ||
| 309 | GPT-5 nano (medium) | OpenAI | 12.50 | - | - | 39.8s | 2025-08-07 | ||
| 310 | GPT-5 nano (minimal) | OpenAI | 7.10 | - | - | 4.27s | 2025-08-07 | ||
| 311 | GPT-5.1 (high) | OpenAI | 24.70 | - | - | 48.6s | 2025-11-13 | ||
| 312 | GPT-5.1 (Non-reasoning) | OpenAI | 13.30 | - | - | 6.84s | 2025-11-13 | ||
| 313 | GPT-5.1 Codex (high) | OpenAI | 23.70 | - | - | - | 2025-11-13 | ||
| 314 | GPT-5.1 Codex mini (high) | OpenAI | 20.40 | - | - | - | 2025-11-13 | ||
| 315 | GPT-5.2 (medium) | OpenAI | 26.50 | - | - | - | 2025-12-11 | ||
| 316 | GPT-5.2 (Non-reasoning) | OpenAI | 17.00 | - | - | 9.01s | 2025-12-11 | ||
| 317 | GPT-5.2 (xhigh) | OpenAI | 30.40 | - | - | 136.7s | 2025-12-11 | ||
| 318 | GPT-5.2 Codex (xhigh) | OpenAI | 28.50 | - | - | - | 2025-12-11 | ||
| 319 | GPT-5.3 Codex (xhigh) | OpenAI | 32.50 | - | - | 62.3s | 2026-02-05 | ||
| 320 | GPT-5.4 (low) | OpenAI | 27.60 | - | - | 7.30s | 2026-03-05 | ||
| 321 | GPT-5.4 (Non-reasoning) | OpenAI | 18.20 | - | - | 6.40s | 2026-03-05 | ||
| 322 | GPT-5.4 (xhigh) | OpenAI | 39.00 | - | - | 113.0s | 2026-03-05 | ||
| 323 | GPT-5.4 mini (medium) | OpenAI | 19.70 | - | - | 8.80s | 2026-03-17 | ||
| 324 | GPT-5.4 mini (Non-Reasoning) | OpenAI | 11.10 | - | - | 4.35s | 2026-03-17 | ||
| 325 | GPT-5.4 nano (medium) | OpenAI | 20.00 | - | - | 9.17s | 2026-03-17 | ||
| 326 | GPT-5.4 nano (Non-Reasoning) | OpenAI | 11.70 | - | - | 4.07s | 2026-03-17 | ||
| 327 | GPT-5.4 Pro (xhigh) | OpenAI | - | - | - | - | 2026-03-05 | ||
| 328 | GPT-5.5 (low) | OpenAI | 30.70 | - | - | 8.68s | 2026-04-23 | ||
| 329 | GPT-5.5 (Non-reasoning) | OpenAI | 23.20 | - | - | 7.51s | 2026-04-23 | ||
| 330 | GPT-5.5 Instant (May 2026) | OpenAI | 22.70 | - | - | - | 2026-05-05 | ||
| 331 | GPT-5.5 Pro (xhigh) | OpenAI | - | - | - | - | 2026-04-23 | ||
| 332 | GPT-5.6 Luna (low) | OpenAI | 21.80 | - | - | 6.83s | 2026-07-09 | ||
| 333 | GPT-5.6 Luna (medium) | OpenAI | 25.80 | - | - | 7.97s | 2026-07-09 | ||
| 334 | GPT-5.6 Luna (Non-reasoning) | OpenAI | 16.80 | - | - | 5.78s | 2026-07-09 | ||
| 335 | GPT-5.6 Sol (Non-reasoning) | OpenAI | 28.30 | - | - | 8.94s | 2026-07-09 | ||
| 336 | GPT-5.6 Terra (Non-reasoning) | OpenAI | 22.30 | - | - | 7.91s | 2026-07-09 | ||
| 337 | GPT-6 Astra (Non-reasoning) | OpenAI | 45.20 | - | - | - | 2026-09-03 | ||
| 338 | gpt-oss-120b (low) | OpenAI | 10.20 | - | - | 12.8s | 2025-08-05 | ||
| 339 | gpt-oss-20b (low) | OpenAI | 10.00 | - | - | 11.9s | 2025-08-05 | ||
| 340 | Granite 3.3 8B (Non-reasoning) | IBM | 4.90 | - | - | 56.8s | 2025-04-16 | ||
| 341 | Granite 4.0 1B | IBM | 5.00 | - | - | - | 2025-10-28 | ||
| 342 | Granite 4.0 350M | IBM | 4.80 | - | - | - | 2025-10-28 | ||
| 343 | Granite 4.0 H 1B | IBM | 5.20 | - | - | - | 2025-10-28 | ||
| 344 | Granite 4.0 H 350M | IBM | 4.80 | - | - | - | 2025-10-28 | ||
| 345 | Granite 4.0 H Small | IBM | 6.00 | - | - | 37.2s | 2025-09-22 | ||
| 346 | Granite 4.0 Micro | IBM | 5.10 | - | - | - | 2025-09-22 | ||
| 347 | Granite 4.1 30B | IBM | 7.40 | - | - | - | 2026-04-29 | ||
| 348 | Granite 4.1 3B | IBM | 5.90 | - | - | - | 2026-04-29 | ||
| 349 | Granite 4.1 8B | IBM | 6.60 | - | - | 6.34s | 2026-04-29 | ||
| 350 | Granite 4.2 30B | IBM | 14.80 | - | - | 33.5s | 2026-08-25 | ||
| 351 | Grok 2 (Dec '24) | SpaceXAI | 7.10 | - | - | - | 2024-12-12 | ||
| 352 | Grok 3 | SpaceXAI | 12.10 | - | - | - | 2025-02-19 | ||
| 353 | Grok 3 mini Reasoning (high) | SpaceXAI | 14.60 | - | - | 46.1s | 2025-02-19 | ||
| 354 | Grok 3 Reasoning Beta | SpaceXAI | 10.40 | - | - | - | 2025-02-19 | ||
| 355 | Grok 4 | SpaceXAI | 22.50 | - | - | - | 2025-07-10 | ||
| 356 | Grok 4 Fast (Non-reasoning) | SpaceXAI | 11.10 | - | - | - | 2025-09-19 | ||
| 357 | Grok 4 Fast (Reasoning) | SpaceXAI | 17.90 | - | - | - | 2025-09-19 | ||
| 358 | Grok 4.1 Fast (Non-reasoning) | SpaceXAI | 11.30 | - | - | - | 2025-11-19 | ||
| 359 | Grok 4.1 Fast (Reasoning) | SpaceXAI | 20.40 | - | - | - | 2025-11-19 | ||
| 360 | Grok 4.20 0309 (Non-reasoning) | SpaceXAI | 14.60 | - | - | - | 2026-03-10 | ||
| 361 | Grok 4.20 0309 (Reasoning) | SpaceXAI | 25.20 | - | - | - | 2026-03-10 | ||
| 362 | Grok 4.20 0309 v2 (Non-reasoning) | SpaceXAI | 14.20 | - | - | 5.84s | 2026-04-07 | ||
| 363 | Grok 4.20 0309 v2 (Reasoning) | SpaceXAI | 25.70 | - | - | 23.8s | 2026-04-07 | ||
| 364 | Grok 4.3 (low) | SpaceXAI | 24.30 | - | - | 10.2s | 2026-04-30 | ||
| 365 | Grok 4.3 (medium) | SpaceXAI | 24.80 | - | - | 16.5s | 2026-04-30 | ||
| 366 | Grok Beta | SpaceXAI | 6.90 | - | - | - | 2024-08-13 | ||
| 367 | Grok Build 0.1 0616 | SpaceXAI | 27.20 | - | - | 39.5s | 2026-06-16 | ||
| 368 | Grok Code Fast 1 | SpaceXAI | 14.10 | - | - | - | 2025-08-28 | ||
| 369 | Grok-1 | SpaceXAI | 6.30 | - | - | - | 2024-03-17 | ||
| 370 | Hermes 3 - Llama-3.1 70B | Nous Research | 6.00 | - | - | 19.0s | 2024-08-15 | ||
| 371 | Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 7.40 | - | - | 13.7s | 2025-08-27 | ||
| 372 | Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 7.50 | - | - | 61.1s | 2025-08-27 | ||
| 373 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 6.70 | - | - | - | 2025-08-27 | ||
| 374 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 7.90 | - | - | - | 2025-08-27 | ||
| 375 | Hy3-preview (Non-reasoning) | Tencent | 17.00 | - | - | - | 2026-04-23 | ||
| 376 | Hy3-preview (Reasoning) | Tencent | 22.70 | - | - | - | 2026-04-23 | ||
| 377 | HyperCLOVA X SEED Think (32B) | Naver | 11.40 | - | - | - | 2025-12-26 | ||
| 378 | HyperNova 60B 2605 (high, based on gpt-oss-120b) | Multiverse Computing | 11.70 | - | - | 7.76s | 2026-05-26 | ||
| 379 | INTELLECT-3 | Prime Intellect | 10.60 | - | - | - | 2025-11-27 | ||
| 380 | Jamba 1.5 Large | AI21 Labs | 6.00 | - | - | - | 2024-08-22 | ||
| 381 | Jamba 1.5 Mini | AI21 Labs | 5.20 | - | - | - | 2024-08-22 | ||
| 382 | Jamba 1.6 Large | AI21 Labs | 6.00 | - | - | - | 2025-03-06 | ||
| 383 | Jamba 1.6 Mini | AI21 Labs | 5.20 | - | - | - | 2025-03-06 | ||
| 384 | Jamba 1.7 Large | AI21 Labs | 6.10 | - | - | - | 2025-07-07 | ||
| 385 | Jamba 1.7 Mini | AI21 Labs | 5.20 | - | - | - | 2025-07-07 | ||
| 386 | Jamba Reasoning 3B | AI21 Labs | 5.70 | - | - | - | 2025-10-08 | ||
| 387 | JT-35B-Flash | China Mobile | 18.70 | - | - | - | 2026-05-14 | ||
| 388 | JT-4.1 Flash 236B A21B | China Mobile | 27.30 | - | - | - | 2026-07-09 | ||
| 389 | JT-MINI | China Mobile | 12.20 | - | - | - | 2026-04-15 | ||
| 390 | K-EXAONE (Non-reasoning) | LG AI Research | 11.20 | - | - | - | 2025-12-31 | ||
| 391 | K-EXAONE (Reasoning) | LG AI Research | 14.40 | - | - | - | 2025-12-31 | ||
| 392 | K-EXAONE 2.0 | LG AI Research | 19.70 | - | - | - | 2026-08-12 | ||
| 393 | K2 Horizon 375B A23B | Foundation Models的MBZUAI Institute | 33.90 | - | - | - | 2026-09-03 | ||
| 394 | K2 Think V2 | Foundation Models的MBZUAI Institute | 11.50 | - | - | - | 2025-12-15 | ||
| 395 | K2-V2 (high) | Foundation Models的MBZUAI Institute | 9.90 | - | - | - | 2025-12-05 | ||
| 396 | K2-V2 (low) | Foundation Models的MBZUAI Institute | 7.30 | - | - | - | 2025-12-05 | ||
| 397 | K2-V2 (medium) | Foundation Models的MBZUAI Institute | 9.00 | - | - | - | 2025-12-05 | ||
| 398 | KAT Coder Pro V2 | KwaiKAT | 21.70 | - | - | - | 2026-03-27 | ||
| 399 | KAT-Coder-Pro V1 | KwaiKAT | 18.60 | - | - | - | 2025-11-11 | ||
| 400 | Kimi K2 | Kimi | 12.70 | - | - | 14.1s | 2025-07-11 | ||
| 401 | Kimi K2 0905 | Kimi | 15.30 | - | - | 13.8s | 2025-09-05 | ||
| 402 | Kimi K2 Thinking | Kimi | 22.00 | - | - | 22.8s | 2025-11-06 | ||
| 403 | Kimi K2.5 (Non-reasoning) | Kimi | 19.40 | - | - | - | 2026-01-27 | ||
| 404 | Kimi K2.5 (Reasoning) | Kimi | 23.50 | - | - | - | 2026-01-27 | ||
| 405 | Kimi K2.6 | Kimi | 31.30 | - | - | 114.4s | 2026-04-20 | ||
| 406 | Kimi K2.6 (Non-reasoning) | Kimi | 23.60 | - | - | 14.2s | 2026-04-20 | ||
| 407 | Kimi K3 (low) | Kimi | 34.50 | - | - | 69.4s | 2026-07-16 | ||
| 408 | Kimi Linear 48B A3B Instruct | Kimi | 7.30 | - | - | - | 2025-10-30 | ||
| 409 | LFM 40B | Liquid AI | 5.40 | - | - | - | 2024-09-30 | ||
| 410 | LFM2 1.2B | Liquid AI | 4.80 | - | - | - | 2025-07-10 | ||
| 411 | LFM2 2.6B | Liquid AI | 5.20 | - | - | - | 2025-09-23 | ||
| 412 | LFM2 24B A2B | Liquid AI | 5.90 | - | - | - | 2026-02-25 | ||
| 413 | LFM2 8B A1B | Liquid AI | 4.90 | - | - | - | 2025-10-07 | ||
| 414 | LFM2.5-1.2B-Instruct | Liquid AI | 5.20 | - | - | - | 2026-01-05 | ||
| 415 | LFM2.5-1.2B-Thinking | Liquid AI | 5.20 | - | - | - | 2026-01-20 | ||
| 416 | LFM2.5-2.6B | Liquid AI | 8.40 | - | - | 14.4s | 2026-08-04 | ||
| 417 | LFM2.5-8B-A1B | Liquid AI | 7.20 | - | - | - | 2026-05-28 | ||
| 418 | LFM2.5-VL-1.6B | Liquid AI | 4.80 | - | - | - | 2026-01-05 | ||
| 419 | Ling 2.6 Flash | InclusionAI | 9.70 | - | - | - | 2026-04-21 | ||
| 420 | Ling 3.0 Flash | InclusionAI | 24.90 | - | - | 11.3s | 2026-08-04 | ||
| 421 | Ling-1T | InclusionAI | 9.20 | - | - | - | 2025-10-08 | ||
| 422 | Ling-2.6-1T | InclusionAI | 17.00 | - | - | - | 2026-04-23 | ||
| 423 | Ling-3.0-flash-VL | InclusionAI | 24.80 | - | - | 19.3s | 2026-09-10 | ||
| 424 | Ling-flash-2.0 | InclusionAI | 7.80 | - | - | 112.4s | 2025-09-17 | ||
| 425 | Ling-mini-2.0 | InclusionAI | 5.50 | - | - | - | 2025-09-09 | ||
| 426 | Llama 2 Chat 13B | Meta | 5.30 | - | - | - | 2023-07-18 | ||
| 427 | Llama 2 Chat 70B | Meta | 5.30 | - | - | - | 2023-07-18 | ||
| 428 | Llama 2 Chat 7B | Meta | 5.70 | - | - | - | 2023-07-18 | ||
| 429 | Llama 3 Instruct 70B | Meta | 5.50 | - | - | - | 2024-04-18 | ||
| 430 | Llama 3 Instruct 8B | Meta | 4.80 | - | - | - | 2024-04-18 | ||
| 431 | Llama 3.1 Instruct 405B | Meta | 7.30 | - | - | - | 2024-07-23 | ||
| 432 | Llama 3.1 Instruct 70B | Meta | 6.60 | - | - | 9.66s | 2024-07-23 | ||
| 433 | Llama 3.1 Instruct 8B | Meta | 6.90 | - | - | 4.36s | 2024-07-23 | ||
| 434 | Llama 3.1 Nemotron Instruct 70B | NVIDIA | 6.90 | - | - | 17.3s | 2024-10-15 | ||
| 435 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 7.30 | - | - | - | 2025-05-20 | ||
| 436 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 7.50 | - | - | - | 2025-04-07 | ||
| 437 | Llama 3.1 Tulu3 405B | Allen Institute for AI | 7.20 | - | - | - | 2025-01-30 | ||
| 438 | Llama 3.2 Instruct 11B (Vision) | Meta | 5.40 | - | - | 38.3s | 2024-09-25 | ||
| 439 | Llama 3.2 Instruct 1B | Meta | 4.80 | - | - | - | 2024-09-25 | ||
| 440 | Llama 3.2 Instruct 3B | Meta | 5.70 | - | - | - | 2024-09-25 | ||
| 441 | Llama 3.2 Instruct 90B (Vision) | Meta | 6.40 | - | - | - | 2024-09-25 | ||
| 442 | Llama 3.3 Instruct 70B | Meta | 7.70 | - | - | 7.54s | 2024-12-06 | ||
| 443 | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | NVIDIA | 7.30 | - | - | - | 2025-03-18 | ||
| 444 | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | NVIDIA | 8.90 | - | - | - | 2025-03-18 | ||
| 445 | Llama 65B | Meta | 5.00 | - | - | - | 2023-02-24 | ||
| 446 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 7.40 | - | - | 19.9s | 2025-07-25 | ||
| 447 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | 9.00 | - | - | 49.5s | 2025-07-25 | ||
| 448 | LongCat Flash Lite | LongCat | 11.50 | - | - | - | 2026-01-28 | ||
| 449 | Magistral Medium 1 | Mistral | 9.10 | - | - | - | 2025-06-10 | ||
| 450 | Magistral Medium 1.2 | Mistral | 11.80 | - | - | - | 2025-09-18 | ||
| 451 | Magistral Small 1 | Mistral | 8.20 | - | - | - | 2025-06-10 | ||
| 452 | Magistral Small 1.2 | Mistral | 8.60 | - | - | - | 2025-09-17 | ||
| 453 | Mi:dm K 2.5 Pro | Korea Telecom | 11.00 | - | - | - | 2025-12-11 | ||
| 454 | Mi:dm K 2.5 Pro Preview | Korea Telecom | - | - | - | - | 2025-12-11 | ||
| 455 | MiMo-V2-Flash (Feb 2026) | Xiaomi | 22.40 | - | - | - | 2025-12-16 | ||
| 456 | MiMo-V2-Flash (Non-reasoning) | Xiaomi | 16.00 | - | - | - | 2025-12-16 | ||
| 457 | MiMo-V2-Flash (Reasoning) | Xiaomi | 20.80 | - | - | - | 2025-12-16 | ||
| 458 | MiMo-V2-Omni | Xiaomi | 23.90 | - | - | - | 2026-03-19 | ||
| 459 | MiMo-V2-Omni-0327 | Xiaomi | 25.10 | - | - | - | 2026-03-27 | ||
| 460 | MiMo-V2-Pro | Xiaomi | 28.60 | - | - | - | 2026-03-18 | ||
| 461 | MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 18.30 | - | - | 20.3s | 2026-04-22 | ||
| 462 | MiniCPM-V 4.6 1.3B | OpenBMB | 5.70 | - | - | - | 2026-05-11 | ||
| 463 | MiniCPM5-1B (Non-reasoning) | OpenBMB | 8.70 | - | - | - | 2026-05-25 | ||
| 464 | MiniCPM5-1B (Reasoning) | OpenBMB | 8.80 | - | - | - | 2026-05-25 | ||
| 465 | MiniCPM5-2B | OpenBMB | 13.10 | - | - | - | 2026-09-07 | ||
| 466 | MiniMax M1 40k | MiniMax | 10.00 | - | - | - | 2025-06-17 | ||
| 467 | MiniMax M1 80k | MiniMax | 11.70 | - | - | - | 2025-06-17 | ||
| 468 | MiniMax-M2 | MiniMax | 18.60 | - | - | 32.9s | 2025-10-26 | ||
| 469 | MiniMax-M2.1 | MiniMax | 20.90 | - | - | 32.6s | 2025-12-23 | ||
| 470 | MiniMax-M2.5 | MiniMax | 22.80 | - | - | 32.6s | 2026-02-12 | ||
| 471 | Mistral 7B Instruct | Mistral | 5.00 | - | - | 7.15s | 2023-09-27 | ||
| 472 | Mistral Large (Feb '24) | Mistral | 5.80 | - | - | - | 2024-02-26 | ||
| 473 | Mistral Large 2 (Jul '24) | Mistral | 6.80 | - | - | - | 2024-07-24 | ||
| 474 | Mistral Large 2 (Nov '24) | Mistral | 7.60 | - | - | - | 2024-11-18 | ||
| 475 | Mistral Medium | Mistral | 5.50 | - | - | 6.07s | 2023-12-11 | ||
| 476 | Mistral Medium 3 | Mistral | 9.00 | - | - | 5.92s | 2025-05-07 | ||
| 477 | Mistral Medium 3.1 | Mistral | 9.90 | - | - | 6.17s | 2025-08-12 | ||
| 478 | Mistral Saba | Mistral | 6.50 | - | - | - | 2025-02-17 | ||
| 479 | Mistral Small (Feb '24) | Mistral | 5.50 | - | - | 4.25s | 2024-02-26 | ||
| 480 | Mistral Small (Sep '24) | Mistral | 5.80 | - | - | 4.42s | 2024-09-17 | ||
| 481 | Mistral Small 3 | Mistral | 6.70 | - | - | 4.25s | 2025-01-30 | ||
| 482 | Mistral Small 4 (Non-reasoning) | Mistral | 9.00 | - | - | 4.15s | 2026-03-16 | ||
| 483 | Mixtral 8x22B Instruct | Mistral | 5.70 | - | - | - | 2024-04-17 | ||
| 484 | Mixtral 8x7B Instruct | Mistral | 5.10 | - | - | - | 2023-12-11 | ||
| 485 | Molmo 7B-D | Allen Institute for AI | 5.60 | - | - | - | 2024-09-25 | ||
| 486 | Molmo2-8B | Allen Institute for AI | 5.00 | - | - | - | 2025-12-11 | ||
| 487 | Motif 3 | Motif Technologies | 33.60 | - | - | - | 2026-08-12 | ||
| 488 | Motif 3 (Beta) | Motif Technologies | 32.30 | - | - | - | 2026-07-14 | ||
| 489 | Motif-2-12.7B-Reasoning | Motif Technologies | 9.20 | - | - | - | 2025-12-04 | ||
| 490 | Muse Spark | Meta | 31.30 | - | - | - | 2026-04-08 | ||
| 491 | Nanbeige4.1-3B | Nanbeige | 8.40 | - | - | - | 2026-02-11 | ||
| 492 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 10.30 | - | - | - | 2026-04-29 | ||
| 493 | Nemotron Cascade 2 30B A3B | NVIDIA | 11.70 | - | - | - | 2026-03-19 | ||
| 494 | Nex-N2-Pro | Nex AGI | 28.20 | - | - | 23.3s | 2026-06-02 | ||
| 495 | North Mini Code | Cohere | 12.80 | - | - | 40.0s | 2026-06-09 | ||
| 496 | Nova 2.0 Lite (high) | Amazon | 13.40 | - | - | 33.6s | 2025-10-29 | ||
| 497 | Nova 2.0 Lite (low) | Amazon | 11.80 | - | - | 26.3s | 2025-10-29 | ||
| 498 | Nova 2.0 Lite (medium) | Amazon | 12.50 | - | - | 31.3s | 2025-10-29 | ||
| 499 | Nova 2.0 Lite (Non-reasoning) | Amazon | 8.70 | - | - | 4.26s | 2025-10-29 | ||
| 500 | Nova 2.0 Omni (low) | Amazon | 11.10 | - | - | - | 2025-11-26 | ||
| 501 | Nova 2.0 Omni (medium) | Amazon | 13.60 | - | - | - | 2025-11-26 | ||
| 502 | Nova 2.0 Omni (Non-reasoning) | Amazon | 8.20 | - | - | - | 2025-11-26 | ||
| 503 | Nova 2.0 Pro Preview (low) | Amazon | 12.80 | - | - | 31.4s | 2025-11-27 | ||
| 504 | Nova 2.0 Pro Preview (medium) | Amazon | 14.20 | - | - | 34.0s | 2025-11-27 | ||
| 505 | Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 10.00 | - | - | 6.07s | 2025-11-27 | ||
| 506 | Nova Lite | Amazon | 6.70 | - | - | 3.86s | 2024-12-03 | ||
| 507 | Nova Micro | Amazon | 5.90 | - | - | 2.75s | 2024-12-03 | ||
| 508 | Nova Premier | Amazon | 9.20 | - | - | 18.8s | 2025-04-30 | ||
| 509 | Nova Pro | Amazon | 7.00 | - | - | - | 2024-12-03 | ||
| 510 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | 6.80 | - | - | 3.98s | 2025-12-15 | ||
| 511 | NVIDIA Nemotron 3 Nano 4B | NVIDIA | 7.40 | - | - | - | 2026-03-16 | ||
| 512 | NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA | 5.80 | - | - | 10.0s | 2025-10-28 | ||
| 513 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA | 7.50 | - | - | 63.1s | 2025-10-28 | ||
| 514 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | 6.80 | - | - | 5.62s | 2025-08-18 | ||
| 515 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 7.40 | - | - | 29.5s | 2025-08-18 | ||
| 516 | o1 | OpenAI | 15.20 | - | - | - | 2024-12-05 | ||
| 517 | o1-mini | OpenAI | 9.80 | - | - | - | 2024-09-12 | ||
| 518 | o1-preview | OpenAI | 11.40 | - | - | - | 2024-09-12 | ||
| 519 | o1-pro | OpenAI | 12.40 | - | - | - | 2025-03-19 | ||
| 520 | o3 | OpenAI | 20.20 | - | - | 12.6s | 2025-04-16 | ||
| 521 | o3-mini | OpenAI | 12.50 | - | - | 8.03s | 2025-01-31 | ||
| 522 | o3-mini (high) | OpenAI | 11.00 | - | - | 21.7s | 2025-01-31 | ||
| 523 | o3-pro | OpenAI | 21.90 | - | - | - | 2025-06-10 | ||
| 524 | o4-mini (high) | OpenAI | 16.70 | - | - | 27.1s | 2025-04-16 | ||
| 525 | OLMo 2 32B | Allen Institute for AI | 6.00 | - | - | - | 2025-03-13 | ||
| 526 | OLMo 2 7B | Allen Institute for AI | 5.60 | - | - | - | 2024-11-26 | ||
| 527 | Olmo 3 32B Think | Allen Institute for AI | 6.50 | - | - | - | 2025-11-20 | ||
| 528 | Olmo 3 7B Instruct | Allen Institute for AI | 5.20 | - | - | - | 2025-11-20 | ||
| 529 | Olmo 3 7B Think | Allen Institute for AI | 5.60 | - | - | - | 2025-11-20 | ||
| 530 | Olmo 3.1 32B Instruct | Allen Institute for AI | 6.50 | - | - | - | 2026-01-13 | ||
| 531 | Olmo 3.1 32B Think | Allen Institute for AI | 7.10 | - | - | - | 2025-12-12 | ||
| 532 | OpenChat 3.5 (1210) | OpenChat | 5.30 | - | - | - | 2023-12-18 | ||
| 533 | PALM-2 | 5.40 | - | - | - | 2023-05-10 | |||
| 534 | Phi-3 Mini Instruct 3.8B | Microsoft | 5.80 | - | - | - | 2024-04-23 | ||
| 535 | Phi-4 | Microsoft | 5.90 | - | - | 14.8s | 2024-12-12 | ||
| 536 | Phi-4 Mini Instruct | Microsoft | 6.30 | - | - | 12.0s | 2024-02-26 | ||
| 537 | Phi-4 Multimodal Instruct | Microsoft | 5.80 | - | - | 30.2s | 2025-02-26 | ||
| 538 | Pixtral Large | Mistral | 7.10 | - | - | - | 2024-11-18 | ||
| 539 | Qwen Chat 14B | Alibaba | 5.00 | - | - | - | 2023-09-25 | ||
| 540 | Qwen Chat 72B | Alibaba | 5.40 | - | - | - | 2023-11-30 | ||
| 541 | Qwen1.5 Chat 110B | Alibaba | 5.70 | - | - | - | 2024-04-25 | ||
| 542 | Qwen2 Instruct 72B | Alibaba | 6.30 | - | - | - | 2024-06-07 | ||
| 543 | Qwen2.5 Coder Instruct 32B | Alibaba | 6.70 | - | - | - | 2024-11-11 | ||
| 544 | Qwen2.5 Coder Instruct 7B | Alibaba | 5.80 | - | - | - | 2024-09-19 | ||
| 545 | Qwen2.5 Instruct 32B | Alibaba | 6.90 | - | - | - | 2024-09-19 | ||
| 546 | Qwen2.5 Instruct 72B | Alibaba | 7.70 | - | - | - | 2024-09-19 | ||
| 547 | Qwen2.5 Max | Alibaba | 8.00 | - | - | - | 2025-01-28 | ||
| 548 | Qwen2.5 Turbo | Alibaba | 6.40 | - | - | 7.06s | 2024-11-18 | ||
| 549 | Qwen3 0.6B (Non-reasoning) | Alibaba | 4.80 | - | - | - | 2025-04-28 | ||
| 550 | Qwen3 0.6B (Reasoning) | Alibaba | 4.80 | - | - | - | 2025-04-28 | ||
| 551 | Qwen3 1.7B (Non-reasoning) | Alibaba | 4.90 | - | - | - | 2025-04-28 | ||
| 552 | Qwen3 1.7B (Reasoning) | Alibaba | 5.20 | - | - | - | 2025-04-28 | ||
| 553 | Qwen3 14B (Non-reasoning) | Alibaba | 6.70 | - | - | 10.9s | 2025-04-28 | ||
| 554 | Qwen3 14B (Reasoning) | Alibaba | 6.40 | - | - | 44.5s | 2025-04-28 | ||
| 555 | Qwen3 235B A22B (Non-reasoning) | Alibaba | 8.30 | - | - | 11.0s | 2025-04-28 | ||
| 556 | Qwen3 235B A22B (Reasoning) | Alibaba | 9.50 | - | - | 45.4s | 2025-04-28 | ||
| 557 | Qwen3 235B A22B 2507 Instruct | Alibaba | 12.00 | - | - | 11.0s | 2025-07-21 | ||
| 558 | Qwen3 30B A3B (Non-reasoning) | Alibaba | 6.60 | - | - | 6.81s | 2025-04-28 | ||
| 559 | Qwen3 30B A3B (Reasoning) | Alibaba | 7.60 | - | - | 25.6s | 2025-04-28 | ||
| 560 | Qwen3 30B A3B 2507 Instruct | Alibaba | 7.50 | - | - | 5.43s | 2025-07-29 | ||
| 561 | Qwen3 32B (Non-reasoning) | Alibaba | 7.30 | - | - | 7.15s | 2025-04-28 | ||
| 562 | Qwen3 32B (Reasoning) | Alibaba | 7.20 | - | - | 26.2s | 2025-04-28 | ||
| 563 | Qwen3 4B (Non-reasoning) | Alibaba | 6.60 | - | - | - | 2025-04-28 | ||
| 564 | Qwen3 4B (Reasoning) | Alibaba | 7.20 | - | - | - | 2025-04-28 | ||
| 565 | Qwen3 4B 2507 (Reasoning) | Alibaba | 8.80 | - | - | - | 2025-08-06 | ||
| 566 | Qwen3 4B 2507 Instruct | Alibaba | 6.70 | - | - | - | 2025-08-06 | ||
| 567 | Qwen3 8B (Non-reasoning) | Alibaba | 6.00 | - | - | 16.5s | 2025-04-28 | ||
| 568 | Qwen3 8B (Reasoning) | Alibaba | 5.20 | - | - | 70.6s | 2025-04-28 | ||
| 569 | Qwen3 Coder 30B A3B Instruct | Alibaba | 9.60 | - | - | 8.50s | 2025-07-31 | ||
| 570 | Qwen3 Coder 480B A35B Instruct | Alibaba | 11.90 | - | - | 12.6s | 2025-07-22 | ||
| 571 | Qwen3 Max | Alibaba | 15.60 | - | - | 13.3s | 2025-09-23 | ||
| 572 | Qwen3 Max (Preview) | Alibaba | 12.60 | - | - | 12.8s | 2025-09-05 | ||
| 573 | Qwen3 Max Thinking | Alibaba | 21.30 | - | - | - | 2026-01-26 | ||
| 574 | Qwen3 Max Thinking (Preview) | Alibaba | 16.30 | - | - | 49.2s | 2025-11-03 | ||
| 575 | Qwen3 Next 80B A3B (Reasoning) | Alibaba | 11.20 | - | - | 15.5s | 2025-09-11 | ||
| 576 | Qwen3 Next 80B A3B Instruct | Alibaba | 9.60 | - | - | 5.01s | 2025-09-11 | ||
| 577 | Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 7.80 | - | - | 26.6s | 2025-09-22 | ||
| 578 | Qwen3 Omni 30B A3B Instruct | Alibaba | 6.00 | - | - | 7.06s | 2025-09-22 | ||
| 579 | Qwen3 VL 235B A22B (Reasoning) | Alibaba | 13.40 | - | - | 46.2s | 2025-09-23 | ||
| 580 | Qwen3 VL 235B A22B Instruct | Alibaba | 9.90 | - | - | 12.7s | 2025-09-23 | ||
| 581 | Qwen3 VL 30B A3B (Reasoning) | Alibaba | 9.50 | - | - | 24.5s | 2025-10-03 | ||
| 582 | Qwen3 VL 30B A3B Instruct | Alibaba | 7.90 | - | - | 6.74s | 2025-10-03 | ||
| 583 | Qwen3 VL 32B (Reasoning) | Alibaba | 11.90 | - | - | 30.4s | 2025-10-21 | ||
| 584 | Qwen3 VL 32B Instruct | Alibaba | 8.40 | - | - | 10.3s | 2025-10-21 | ||
| 585 | Qwen3 VL 4B (Reasoning) | Alibaba | 7.00 | - | - | - | 2025-10-14 | ||
| 586 | Qwen3 VL 4B Instruct | Alibaba | 5.70 | - | - | - | 2025-10-14 | ||
| 587 | Qwen3 VL 8B (Reasoning) | Alibaba | 8.20 | - | - | 24.3s | 2025-10-14 | ||
| 588 | Qwen3 VL 8B Instruct | Alibaba | 7.30 | - | - | 6.51s | 2025-10-14 | ||
| 589 | Qwen3.5 0.8B (Non-reasoning) | Alibaba | 5.40 | - | - | - | 2026-03-02 | ||
| 590 | Qwen3.5 0.8B (Reasoning) | Alibaba | 6.10 | - | - | - | 2026-03-02 | ||
| 591 | Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 17.70 | - | - | 5.91s | 2026-02-24 | ||
| 592 | Qwen3.5 27B (Non-reasoning) | Alibaba | 19.40 | - | - | 11.9s | 2026-02-24 | ||
| 593 | Qwen3.5 27B (Reasoning) | Alibaba | 22.90 | - | - | 39.1s | 2026-02-24 | ||
| 594 | Qwen3.5 2B (Non-reasoning) | Alibaba | 6.20 | - | - | - | 2026-03-02 | ||
| 595 | Qwen3.5 2B (Reasoning) | Alibaba | 6.90 | - | - | - | 2026-03-02 | ||
| 596 | Qwen3.5 35B A3B (Non-reasoning) | Alibaba | 15.10 | - | - | 5.33s | 2026-02-24 | ||
| 597 | Qwen3.5 35B A3B (Reasoning) | Alibaba | 19.30 | - | - | 19.5s | 2026-02-24 | ||
| 598 | Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 21.40 | - | - | 8.69s | 2026-02-16 | ||
| 599 | Qwen3.5 4B (Non-reasoning) | Alibaba | 10.80 | - | - | 29.4s | 2026-03-02 | ||
| 600 | Qwen3.5 4B (Reasoning) | Alibaba | 13.10 | - | - | 90.0s | 2026-03-02 | ||
| 601 | Qwen3.5 9B (Non-reasoning) | Alibaba | 13.30 | - | - | 6.48s | 2026-03-02 | ||
| 602 | Qwen3.5 9B (Reasoning) | Alibaba | 13.70 | - | - | 31.4s | 2026-03-02 | ||
| 603 | Qwen3.5 Omni Flash | Alibaba | 12.50 | - | - | 4.12s | 2026-03-30 | ||
| 604 | Qwen3.5 Omni Plus | Alibaba | 20.40 | - | - | 8.00s | 2026-03-30 | ||
| 605 | Qwen3.6 27B (Non-reasoning) | Alibaba | 19.80 | - | - | 12.8s | 2026-04-22 | ||
| 606 | Qwen3.6 35B A3B (Non-reasoning) | Alibaba | 15.20 | - | - | 5.73s | 2026-04-16 | ||
| 607 | Qwen3.6 Max Preview | Alibaba | 28.40 | - | - | 47.0s | 2026-04-20 | ||
| 608 | Qwen3.6 Plus | Alibaba | 27.00 | - | - | 110.0s | 2026-04-02 | ||
| 609 | Qwen3.8 27B (Non-reasoning) | Alibaba | 22.40 | - | - | 14.5s | 2026-08-14 | ||
| 610 | QwQ 32B | Alibaba | 9.50 | - | - | - | 2025-03-05 | ||
| 611 | QwQ 32B-Preview | Alibaba | 7.60 | - | - | - | 2024-11-27 | ||
| 612 | R1 1776 | Perplexity | 6.40 | - | - | - | 2025-02-18 | ||
| 613 | Reka Flash (Sep '24) | Reka AI | 6.40 | - | - | - | 2024-10-04 | ||
| 614 | Reka Flash 3 | Reka AI | 5.60 | - | - | - | 2025-03-10 | ||
| 615 | Ring-1T | InclusionAI | 10.90 | - | - | - | 2025-10-13 | ||
| 616 | Ring-flash-2.0 | InclusionAI | 7.20 | - | - | - | 2025-09-19 | ||
| 617 | Sarvam 105B (high) | Sarvam | 8.80 | - | - | - | 2026-03-06 | ||
| 618 | Sarvam 30B (high) | Sarvam | 6.60 | - | - | - | 2026-03-06 | ||
| 619 | Sarvam M (Reasoning) | Sarvam | 5.30 | - | - | - | 2025-05-23 | ||
| 620 | Seed-OSS-36B-Instruct | ByteDance Seed | 12.10 | - | - | 81.1s | 2025-08-20 | ||
| 621 | Solar Mini | Upstage | 6.40 | - | - | - | 2024-01-25 | ||
| 622 | Solar Open 100B (Reasoning) | Upstage | 10.40 | - | - | - | 2025-12-17 | ||
| 623 | Solar Open2 250B | Upstage | 24.70 | - | - | - | 2026-08-12 | ||
| 624 | Solar Pro 2 (Non-reasoning) | Upstage | 7.00 | - | - | - | 2025-07-09 | ||
| 625 | Solar Pro 2 (Preview) (Non-reasoning) | Upstage | 7.90 | - | - | - | 2025-05-20 | ||
| 626 | Solar Pro 2 (Preview) (Reasoning) | Upstage | 9.10 | - | - | - | 2025-05-20 | ||
| 627 | Solar Pro 2 (Reasoning) | Upstage | 7.50 | - | - | - | 2025-07-09 | ||
| 628 | Solar Pro 4 | Upstage | 28.20 | - | - | 38.7s | 2026-08-06 | ||
| 629 | Sonar | Perplexity | 7.70 | - | - | - | 2025-01-21 | ||
| 630 | Sonar Pro | Perplexity | 7.60 | - | - | - | 2025-01-21 | ||
| 631 | Sonar Reasoning | Perplexity | 8.70 | - | - | - | 2025-01-28 | ||
| 632 | Sonar Reasoning Pro | Perplexity | 11.80 | - | - | - | 2025-01-28 | ||
| 633 | Step 3.5 Flash | StepFun | 16.60 | - | - | 12.9s | 2026-02-02 | ||
| 634 | Step 3.5 Flash 2603 | StepFun | 17.00 | - | - | 12.7s | 2026-04-02 | ||
| 635 | Step 3.7 Flash | StepFun | 19.50 | - | - | 31.0s | 2026-05-29 | ||
| 636 | Step3 VL 10B | StepFun | 7.70 | - | - | - | 2026-01-20 | ||
| 637 | Tiny Aya Global | Cohere | 4.80 | - | - | - | 2026-02-17 | ||
| 638 | Tri-21B-Think | Trillion Labs | 9.00 | - | - | - | 2026-02-10 | ||
| 639 | Tri-21B-think Preview | Trillion Labs | 9.60 | - | - | - | 2026-02-10 |