所有602 LLMs从智能和成本上进行比较
来自 Artificial Analysis 和其他来源的 2026-08-19 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
- 602
- 可下载权重的模型 (open weights)
- 341
- 在帕累托前沿
- 15
- 可下载权重模型前沿（open-weights frontier）
- 15
- 数据快照
- 2026-08-19
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。
- OpenAIGPT-5.6 Luna (Non-reasoning)
- 智能得分 (Intelligence Index)
- 26.80
- 基准测试费用（美元）
- $10.2
- OpenAIGPT-5.6 Luna (low)
- 智能得分 (Intelligence Index)
- 33.90
- 基准测试费用（美元）
- $13.7
- OpenAIGPT-5.6 Luna (medium)
- 智能得分 (Intelligence Index)
- 38.90
- 基准测试费用（美元）
- $21.1
- OpenAIGPT-5.6 Luna (high)
- 智能得分 (Intelligence Index)
- 47.00
- 基准测试费用（美元）
- $55.0
- OpenAIGPT-5.6 Luna (xhigh)
- 智能得分 (Intelligence Index)
- 50.10
- 基准测试费用（美元）
- $95.1
- GoogleGemini 3.7 Flash (low)
- 智能得分 (Intelligence Index)
- 50.90
- 基准测试费用（美元）
- $165
- OpenAIGPT-5.6 Luna (max)
- 智能得分 (Intelligence Index)
- 52.30
- 基准测试费用（美元）
- $172
- GoogleGemini 3.7 Flash (medium)
- 智能得分 (Intelligence Index)
- 53.40
- 基准测试费用（美元）
- $278
- GoogleGemini 3.7 Flash (high)
- 智能得分 (Intelligence Index)
- 56.00
- 基准测试费用（美元）
- $485
- MetaMuse Spark 1.2 (xhigh)
- 智能得分 (Intelligence Index)
- 56.80
- 基准测试费用（美元）
- $639
- OpenAIGPT-5.6 Sol (high)
- 智能得分 (Intelligence Index)
- 57.30
- 基准测试费用（美元）
- $955
- SpaceXAIGrok 4.6 (high)
- 智能得分 (Intelligence Index)
- 60.90
- 基准测试费用（美元）
- $1068
- AnthropicClaude Opus 5 (Adaptive Reasoning, High Effort)
- 智能得分 (Intelligence Index)
- 61.50
- 基准测试费用（美元）
- $1974
- AnthropicClaude Opus 5 (Adaptive Reasoning, Xhigh Effort)
- 智能得分 (Intelligence Index)
- 62.50
- 基准测试费用（美元）
- $2909
- AnthropicClaude Opus 5 (Adaptive Reasoning, Max Effort)
- 智能得分 (Intelligence Index)
- 63.10
- 基准测试费用（美元）
- $3836
Last 30 天
最新发布
Z AI · 2026-08-18GLM-5.3
- 今天
- 不在前沿
- 发布日期
- 不在前沿
还没有基准数据
DeepSeek · 2026-08-13可下载权重的模型 (open weights)DeepSeek V4 Pro 0813- 今天
- 可下载权重模型前沿（open-weights frontier）
- 发布日期
- 可下载权重模型前沿（open-weights frontier）
- 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
SpaceXAI · 2026-08-12Grok 4.6- 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
Motif Technologies · 2026-08-12可下载权重的模型 (open weights)Motif 3还没有基准数据
602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 | GPT-5.6 Luna (Non-reasoning) | OpenAI | 26.80 | $10.2 | 2.62 | 4.15s | 2026-07-09 | 最佳性价比前沿 | |
| 2 | GPT-5.6 Luna (low) | OpenAI | 33.90 | $13.7 | 2.47 | 5.37s | 2026-07-09 | 最佳性价比前沿 | |
| 3 | GPT-5.6 Luna (medium) | OpenAI | 38.90 | $21.1 | 1.84 | 6.41s | 2026-07-09 | 最佳性价比前沿 | |
| 4 | MiMo-V2.5 | Xiaomi | 38.00 | $25.2 | 1.51 | 47.7s | 2026-04-22 | 开放权重前沿 | |
| 5 | Llama 4 Scout | Meta | 10.30 | $11.6 | 0.89 | 4.49s | 2025-04-05 | 开放权重前沿 | |
| 6 | GPT-5.6 Luna (high) | OpenAI | 47.00 | $55.0 | 0.85 | 14.6s | 2026-07-09 | 最佳性价比前沿 | |
| 7 | DeepSeek V3 (Dec '24) | DeepSeek | 14.20 | $20.0 | 0.71 | - | 2024-12-26 | 开放权重前沿 | |
| 8 | DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | 39.00 | $57.0 | 0.68 | - | 2026-04-24 | 开放权重前沿 | |
| 9 | Gemma 4 31B (Non-reasoning) | 22.30 | $33.8 | 0.66 | 7.47s | 2026-04-02 | |||
| 10 | gpt-oss-120b (low) | OpenAI | 14.90 | $24.2 | 0.62 | 16.5s | 2025-08-05 | 开放权重前沿 | |
| 11 | GPT-5.6 Luna (xhigh) | OpenAI | 50.10 | $95.1 | 0.53 | 49.3s | 2026-07-09 | 最佳性价比前沿 | |
| 12 | Ling 3.0 Flash | InclusionAI | 37.80 | $72.8 | 0.52 | - | 2026-08-04 | ||
| 13 | Mistral Small 3.1 | Mistral | 14.90 | $29.8 | 0.50 | 4.16s | 2025-03-17 | ||
| 14 | Gemma 4 26B A4B (Reasoning) | 26.10 | $53.9 | 0.48 | - | 2026-04-02 | |||
| 15 | gpt-oss-20b (high) | OpenAI | 15.20 | $32.7 | 0.46 | 19.4s | 2025-08-05 | ||
| 16 | Hy3 | Tencent | 42.20 | $93.2 | 0.45 | 40.1s | 2026-07-06 | 开放权重前沿 | |
| 17 | MiMo-V2.5-Pro | Xiaomi | 42.90 | $98.9 | 0.43 | 45.9s | 2026-04-22 | 开放权重前沿 | |
| 18 | DeepSeek V3 0324 | DeepSeek | 15.20 | $35.2 | 0.43 | - | 2025-03-25 | ||
| 19 | DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | 42.10 | $104 | 0.40 | - | 2026-04-24 | ||
| 20 | Llama 4 Maverick | Meta | 14.50 | $35.9 | 0.40 | 5.37s | 2025-04-05 | ||
| 21 | DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 43.70 | $109 | 0.40 | 35.0s | 2026-04-24 | 开放权重前沿 | |
| 22 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 14.50 | $39.4 | 0.37 | 12.0s | 2025-12-15 | ||
| 23 | GPT-5.6 Terra (Non-reasoning) | OpenAI | 34.60 | $98.5 | 0.35 | 5.90s | 2026-07-09 | ||
| 24 | Muse Glimmer (high) | Meta | 35.10 | $105 | 0.33 | 23.4s | 2026-08-10 | ||
| 25 | Nemotron 3.5 Lightning | NVIDIA | 23.60 | $71.5 | 0.33 | 9.43s | 2026-08-11 | ||
| 26 | GPT-5.6 Terra (low) | OpenAI | 41.30 | $130 | 0.32 | 6.86s | 2026-07-09 | ||
| 27 | Gemini 3.7 Flash (low) | 50.90 | $165 | 0.31 | 2.48s | 2026-08-13 | 最佳性价比前沿 | ||
| 28 | GPT-5.6 Luna (max) | OpenAI | 52.30 | $172 | 0.30 | 162.6s | 2026-07-09 | 最佳性价比前沿 | |
| 29 | Gemini 3.1 Flash-Lite | 25.60 | $93.8 | 0.27 | 7.21s | 2026-03-03 | |||
| 30 | MiniMax-M2.7 | MiniMax | 38.90 | $143 | 0.27 | 50.7s | 2026-03-18 | ||
| 31 | GPT-4.1 nano | OpenAI | 9.60 | $36.7 | 0.26 | 4.68s | 2025-04-14 | ||
| 32 | DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 45.30 | $176 | 0.26 | 67.6s | 2026-04-24 | 开放权重前沿 | |
| 33 | gpt-oss-120b (high) | OpenAI | 24.10 | $95.0 | 0.25 | 16.4s | 2025-08-05 | ||
| 34 | Gemini 3.5 Flash-Lite | 37.40 | $153 | 0.24 | 11.3s | 2026-07-21 | |||
| 35 | GPT-5.6 Terra (medium) | OpenAI | 46.80 | $192 | 0.24 | 7.09s | 2026-07-09 | ||
| 36 | GPT-4.1 mini | OpenAI | 14.80 | $64.2 | 0.23 | 5.84s | 2025-04-14 | ||
| 37 | Mistral Small 4 (Reasoning) | Mistral | 19.70 | $87.7 | 0.22 | 16.4s | 2026-03-16 | ||
| 38 | Mercury 2 | Inception | 21.90 | $97.5 | 0.22 | 4.53s | 2026-02-20 | ||
| 39 | Mistral Large 3 | Mistral | 15.90 | $71.1 | 0.22 | 11.6s | 2025-12-02 | ||
| 40 | MiniMax-M3 | MiniMax | 45.40 | $205 | 0.22 | 29.1s | 2026-06-01 | 开放权重前沿 | |
| 41 | Inkling Small | Thinking Machines | 41.20 | $193 | 0.21 | 39.3s | 2026-07-30 | ||
| 42 | Qwen3 Next 80B A3B (Reasoning) | Alibaba | 16.90 | $84.0 | 0.20 | 14.9s | 2025-09-11 | ||
| 43 | GPT-5 mini (high) | OpenAI | 25.80 | $130 | 0.20 | 95.4s | 2025-08-07 | ||
| 44 | Gemini 3.7 Flash (medium) | 53.40 | $278 | 0.19 | 6.21s | 2026-08-13 | 最佳性价比前沿 | ||
| 45 | GPT-5.6 Sol (Non-reasoning) | OpenAI | 41.90 | $240 | 0.17 | 9.66s | 2026-07-09 | ||
| 46 | Kimi K3 (low) | Kimi | 48.30 | $283 | 0.17 | 71.8s | 2026-07-16 | 开放权重前沿 | |
| 47 | GPT-5.5 (Non-reasoning) | OpenAI | 35.80 | $212 | 0.17 | 8.28s | 2026-04-23 | ||
| 48 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 51.80 | $323 | 0.16 | 25.4s | 2026-07-31 | 开放权重前沿 | |
| 49 | GPT-5.6 Sol (low) | OpenAI | 50.70 | $344 | 0.15 | 12.3s | 2026-07-09 | ||
| 50 | GPT-5.4 nano (xhigh) | OpenAI | 39.70 | $277 | 0.14 | 6.82s | 2026-03-17 | ||
| 51 | Grok 4.3 (high) | SpaceXAI | 37.90 | $288 | 0.13 | 24.7s | 2026-04-30 | ||
| 52 | Solar Pro 4 | Upstage | 41.60 | $321 | 0.13 | 55.9s | 2026-08-06 | ||
| 53 | Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 28.20 | $221 | 0.13 | 5.84s | 2026-02-24 | ||
| 54 | GPT-5.6 Terra (high) | OpenAI | 50.10 | $395 | 0.13 | 7.61s | 2026-07-09 | ||
| 55 | Gemini 3.6 Flash (high) | 51.60 | $412 | 0.13 | 21.0s | 2026-07-21 | |||
| 56 | Grok 4.3 (Non-reasoning) | SpaceXAI | 25.00 | $201 | 0.12 | 5.95s | 2026-04-30 | ||
| 57 | Qwen3.7 Plus | Alibaba | 39.40 | $322 | 0.12 | 46.4s | 2026-06-01 | ||
| 58 | GPT-5.5 (low) | OpenAI | 44.50 | $374 | 0.12 | 8.81s | 2026-04-23 | ||
| 59 | Kimi K2.5 (Reasoning) | Kimi | 36.00 | $304 | 0.12 | 83.4s | 2026-01-27 | ||
| 60 | Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 19.90 | $170 | 0.12 | 41.6s | 2025-07-25 | ||
| 61 | Gemini 3.7 Flash (high) | 56.00 | $485 | 0.12 | 16.7s | 2026-08-13 | 最佳性价比前沿 | ||
| 62 | Mistral Medium 3.1 | Mistral | 14.70 | $134 | 0.11 | 6.17s | 2025-08-12 | ||
| 63 | Grok Build 0.1 0616 | SpaceXAI | 40.70 | $377 | 0.11 | 46.1s | 2026-06-16 | ||
| 64 | Qwen3.5 35B A3B (Non-reasoning) | Alibaba | 24.30 | $228 | 0.11 | 5.08s | 2026-02-24 | ||
| 65 | Claude Sonnet 5 (Non-reasoning, High Effort) | Anthropic | 42.60 | $416 | 0.10 | 10.1s | 2026-06-30 | ||
| 66 | Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 25.70 | $254 | 0.10 | 21.4s | 2026-03-11 | ||
| 67 | Muse Spark 1.1 (xhigh) | Meta | 53.20 | $547 | 0.10 | 14.0s | 2026-07-09 | ||
| 68 | Step 3.7 Flash | StepFun | 30.90 | $320 | 0.10 | 24.1s | 2026-05-29 | ||
| 69 | Grok 4.5 (high) | SpaceXAI | 55.80 | $579 | 0.10 | 24.1s | 2026-07-08 | ||
| 70 | Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 14.60 | $152 | 0.10 | 20.5s | 2025-07-30 | ||
| 71 | GPT-5.6 Sol (medium) | OpenAI | 55.60 | $580 | 0.10 | 12.6s | 2026-07-09 | ||
| 72 | Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 52.50 | $555 | 0.09 | 13.7s | 2026-07-24 | ||
| 73 | Ministral 3 14B | Mistral | 11.20 | $119 | 0.09 | 6.18s | 2025-12-02 | ||
| 74 | GLM-4.6 (Reasoning) | Z AI | 29.30 | $314 | 0.09 | 52.7s | 2025-09-30 | ||
| 75 | Solar Pro 3 | Upstage | 14.50 | $158 | 0.09 | 18.9s | 2026-04-06 | ||
| 76 | Qwen3.5 9B (Reasoning) | Alibaba | 21.80 | $240 | 0.09 | 33.0s | 2026-03-02 | ||
| 77 | GPT-5.6 Terra (xhigh) | OpenAI | 52.80 | $590 | 0.09 | 31.9s | 2026-07-09 | ||
| 78 | Muse Spark 1.2 (xhigh) | Meta | 56.80 | $639 | 0.09 | - | 2026-08-05 | 最佳性价比前沿 | |
| 79 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 53.20 | $605 | 0.09 | 35.2s | 2026-08-13 | 开放权重前沿 | |
| 80 | Qwen3.6 27B (Non-reasoning) | Alibaba | 31.30 | $359 | 0.09 | 12.7s | 2026-04-22 | ||
| 81 | Qwen3 Coder Next | Alibaba | 21.30 | $250 | 0.09 | 4.97s | 2026-02-03 | ||
| 82 | Mistral Small 3.2 | Mistral | 10.70 | $129 | 0.08 | 4.18s | 2025-06-20 | ||
| 83 | Celeris-1 | Celeris | 12.40 | $157 | 0.08 | 0.95s | 2026-07-24 | ||
| 84 | Kimi K2.7 Code | Kimi | 43.00 | $545 | 0.08 | 75.9s | 2026-06-12 | ||
| 85 | Ministral 3 8B | Mistral | 9.00 | $114 | 0.08 | 4.90s | 2025-12-02 | ||
| 86 | Ministral 3 3B | Mistral | 7.10 | $91.6 | 0.08 | 3.10s | 2025-12-02 | ||
| 87 | Qwen3.6 Plus | Alibaba | 40.50 | $526 | 0.08 | 109.5s | 2026-04-02 | ||
| 88 | LongCat 2.0 | LongCat | 34.00 | $442 | 0.08 | 66.4s | 2026-06-29 | ||
| 89 | Qwen3.5 122B A10B (Reasoning) | Alibaba | 32.80 | $444 | 0.07 | 21.5s | 2026-02-24 | ||
| 90 | Trinity Large Thinking | Arcee AI | 18.70 | $255 | 0.07 | 14.1s | 2026-04-01 | ||
| 91 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 38.30 | $534 | 0.07 | 23.1s | 2026-06-04 | ||
| 92 | Ring-2.6-1T | InclusionAI | 31.70 | $455 | 0.07 | - | 2026-05-08 | ||
| 93 | GPT-5.5 Instant (June 2026) | OpenAI | 29.20 | $423 | 0.07 | 22.4s | 2026-06-25 | ||
| 94 | Qwen3.5 397B A17B (Reasoning) | Alibaba | 34.30 | $527 | 0.07 | 44.0s | 2026-02-16 | ||
| 95 | Qwen3.6 35B A3B (Reasoning) | Alibaba | 32.10 | $505 | 0.06 | 52.0s | 2026-04-16 | ||
| 96 | Claude 4.5 Haiku (Reasoning) | Anthropic | 29.90 | $471 | 0.06 | 22.3s | 2025-10-15 | ||
| 97 | GLM-5.2 (max) | Z AI | 52.60 | $843 | 0.06 | 23.8s | 2026-06-16 | ||
| 98 | Inkling (xhigh) | Thinking Machines | 42.30 | $698 | 0.06 | 35.5s | 2026-07-15 | ||
| 99 | GPT-5.6 Sol (high) | OpenAI | 57.30 | $955 | 0.06 | 24.0s | 2026-07-09 | 最佳性价比前沿 | |
| 100 | Gemini 3.1 Pro Preview | 47.70 | $812 | 0.06 | 37.1s | 2026-02-19 | |||
| 101 | GLM-5.1 (Reasoning) | Z AI | 41.00 | $700 | 0.06 | 53.4s | 2026-04-07 | ||
| 102 | Grok 4.6 (high) | SpaceXAI | 60.90 | $1068 | 0.06 | 45.7s | 2026-08-12 | 最佳性价比前沿 | |
| 103 | GLM-4.7 (Reasoning) | Z AI | 34.50 | $607 | 0.06 | 24.4s | 2025-12-22 | ||
| 104 | Qwen3.6 27B (Reasoning) | Alibaba | 37.70 | $667 | 0.06 | 115.6s | 2026-04-22 | ||
| 105 | GPT-5.5 (medium) | OpenAI | 51.40 | $939 | 0.05 | 13.2s | 2026-04-23 | ||
| 106 | Kimi K2.6 | Kimi | 45.10 | $841 | 0.05 | 111.1s | 2026-04-20 | ||
| 107 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 58.60 | $1116 | 0.05 | 16.1s | 2026-07-24 | ||
| 108 | Gemini 3.5 Flash (high) | 52.00 | $1042 | 0.05 | 30.2s | 2026-05-19 | |||
| 109 | GLM-5.3 (max) | Z AI | 59.50 | $1239 | 0.05 | 31.4s | 2026-08-18 | ||
| 110 | GPT-5.1 (high) | OpenAI | 37.50 | $782 | 0.05 | 32.9s | 2025-11-13 | ||
| 111 | Qwen3.6 35B A3B (Non-reasoning) | Alibaba | 24.60 | $530 | 0.05 | 5.83s | 2026-04-16 | ||
| 112 | GPT-5 (high) | OpenAI | 35.30 | $789 | 0.04 | 105.0s | 2025-08-07 | ||
| 113 | DeepSeek R1 (Jan '25) | DeepSeek | 18.60 | $417 | 0.04 | - | 2025-01-20 | ||
| 114 | Qwen3.7 Max | Alibaba | 46.70 | $1064 | 0.04 | 16.7s | 2026-05-19 | ||
| 115 | Gemini 2.5 Pro | 25.90 | $611 | 0.04 | 24.2s | 2025-06-05 | |||
| 116 | GPT-5.6 Terra (max) | OpenAI | 56.60 | $1390 | 0.04 | 190.9s | 2026-07-09 | ||
| 117 | GPT-5.6 Sol (xhigh) | OpenAI | 59.00 | $1525 | 0.04 | 58.8s | 2026-07-09 | ||
| 118 | Magistral Small 1.2 | Mistral | 11.50 | $301 | 0.04 | 18.3s | 2025-09-17 | ||
| 119 | GPT-5.4 mini (xhigh) | OpenAI | 40.90 | $1096 | 0.04 | 15.0s | 2026-03-17 | ||
| 120 | Claude 4.5 Sonnet (Reasoning) | Anthropic | 37.40 | $1037 | 0.04 | 24.8s | 2025-09-29 | ||
| 121 | Qwen3.8 2.4T A95B | Alibaba | 57.70 | $1672 | 0.03 | 56.8s | 2026-08-12 | 开放权重前沿 | |
| 122 | Mistral Medium 3.5 | Mistral | 30.40 | $883 | 0.03 | 21.2s | 2026-04-29 | ||
| 123 | Qwen3.8 Max | Alibaba | 58.10 | $1741 | 0.03 | 58.8s | 2026-08-03 | ||
| 124 | GPT-5.5 (high) | OpenAI | 54.70 | $1721 | 0.03 | 30.5s | 2026-04-23 | ||
| 125 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 61.50 | $1974 | 0.03 | 30.3s | 2026-07-24 | 最佳性价比前沿 | |
| 126 | Kimi K3 (max) | Kimi | 59.70 | $2425 | 0.02 | 68.9s | 2026-07-16 | 开放权重前沿 | |
| 127 | GPT-5.4 (xhigh) | OpenAI | 53.10 | $2183 | 0.02 | 147.9s | 2026-03-05 | ||
| 128 | GPT-5.6 Sol (max) | OpenAI | 60.90 | $2823 | 0.02 | 216.4s | 2026-07-09 | ||
| 129 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 62.50 | $2909 | 0.02 | 49.8s | 2026-07-24 | 最佳性价比前沿 | |
| 130 | GPT-5.5 (xhigh) | OpenAI | 56.30 | $2778 | 0.02 | 74.7s | 2026-04-23 | ||
| 131 | Magistral Medium 1.2 | Mistral | 18.00 | $920 | 0.02 | 22.0s | 2025-09-18 | ||
| 132 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 63.10 | $3836 | 0.02 | 69.4s | 2026-07-24 | 最佳性价比前沿 | |
| 133 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 57.30 | $3752 | 0.02 | 31.5s | 2026-05-28 | ||
| 134 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 55.00 | $3743 | 0.01 | 26.1s | 2026-04-16 | ||
| 135 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 48.40 | $3355 | 0.01 | 158.4s | 2026-02-17 | ||
| 136 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 55.30 | $4011 | 0.01 | 191.1s | 2026-06-30 | ||
| 137 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 62.10 | $5455 | 0.01 | 155.6s | 2026-06-09 | ||
| 138 | A.X-K2 | SK Telecom | 35.00 | - | - | - | 2026-08-12 | ||
| 139 | Agnes 2.5 Pro Alpha | Sapiens AI | 39.70 | - | - | 21.0s | 2026-07-24 | ||
| 140 | Apertus 70B Instruct | Swiss AI Initiative | 2.00 | - | - | - | 2025-09-02 | ||
| 141 | Apertus 8B Instruct | Swiss AI Initiative | 1.00 | - | - | - | 2025-09-02 | ||
| 142 | Apriel-v1.5-15B-Thinker | ServiceNow | 21.60 | - | - | - | 2025-09-30 | ||
| 143 | Apriel-v1.6-15B-Thinker | ServiceNow | 20.80 | - | - | - | 2025-11-25 | ||
| 144 | Arctic Instruct | Snowflake | 3.00 | - | - | - | 2024-04-24 | ||
| 145 | Claude 2.0 | Anthropic | 3.30 | - | - | - | 2023-07-11 | ||
| 146 | Claude 2.1 | Anthropic | 3.50 | - | - | - | 2023-11-21 | ||
| 147 | Claude 3 Haiku | Anthropic | 3.50 | - | - | - | 2024-03-04 | ||
| 148 | Claude 3 Opus | Anthropic | 11.80 | - | - | - | 2024-03-04 | ||
| 149 | Claude 3 Sonnet | Anthropic | 4.40 | - | - | - | 2024-03-04 | ||
| 150 | Claude 3.5 Haiku | Anthropic | 12.20 | - | - | - | 2024-10-22 | ||
| 151 | Claude 3.5 Sonnet (June '24) | Anthropic | 8.10 | - | - | - | 2024-06-21 | ||
| 152 | Claude 3.5 Sonnet (Oct '24) | Anthropic | 9.80 | - | - | - | 2024-10-22 | ||
| 153 | Claude 3.7 Sonnet (Non-reasoning) | Anthropic | 23.90 | - | - | - | 2025-02-24 | ||
| 154 | Claude 3.7 Sonnet (Reasoning) | Anthropic | 27.60 | - | - | - | 2025-02-24 | ||
| 155 | Claude 4 Opus (Non-reasoning) | Anthropic | 26.00 | - | - | - | 2025-05-22 | ||
| 156 | Claude 4 Opus (Reasoning) | Anthropic | 31.70 | - | - | - | 2025-05-22 | ||
| 157 | Claude 4 Sonnet (Non-reasoning) | Anthropic | 26.00 | - | - | - | 2025-05-22 | ||
| 158 | Claude 4 Sonnet (Reasoning) | Anthropic | 29.80 | - | - | - | 2025-05-22 | ||
| 159 | Claude 4.1 Opus (Non-reasoning) | Anthropic | 28.80 | - | - | - | 2025-08-05 | ||
| 160 | Claude 4.1 Opus (Reasoning) | Anthropic | 34.50 | - | - | - | 2025-08-05 | ||
| 161 | Claude 4.5 Haiku (Non-reasoning) | Anthropic | 24.10 | - | - | 6.59s | 2025-10-15 | ||
| 162 | Claude 4.5 Sonnet (Non-reasoning) | Anthropic | 29.90 | - | - | 14.3s | 2025-09-29 | ||
| 163 | Claude Instant | Anthropic | 1.70 | - | - | - | 2023-03-14 | ||
| 164 | Claude Opus 4.5 (Non-reasoning) | Anthropic | 35.60 | - | - | 12.7s | 2025-11-24 | ||
| 165 | Claude Opus 4.5 (Reasoning) | Anthropic | 41.90 | - | - | 22.2s | 2025-11-24 | ||
| 166 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 44.90 | - | - | 28.3s | 2026-02-05 | ||
| 167 | Claude Opus 4.6 (Non-reasoning, High Effort) | Anthropic | 38.80 | - | - | 16.1s | 2026-02-05 | ||
| 168 | Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic | 43.90 | - | - | 12.7s | 2026-04-16 | ||
| 169 | Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic | 36.80 | - | - | 12.9s | 2026-02-17 | ||
| 170 | Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 35.10 | - | - | 13.0s | 2026-02-17 | ||
| 171 | Claude Sonnet 5 (Adaptive Reasoning, High Effort) | Anthropic | - | - | - | 19.8s | 2026-06-30 | ||
| 172 | Claude Sonnet 5 (Adaptive Reasoning, Low Effort) | Anthropic | - | - | - | 10.7s | 2026-06-30 | ||
| 173 | Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) | Anthropic | - | - | - | 11.5s | 2026-06-30 | ||
| 174 | Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | - | - | - | 42.7s | 2026-06-30 | ||
| 175 | Cogito v2.1 (Reasoning) | Deep Cogito | - | - | - | - | 2025-11-18 | ||
| 176 | Command A | Cohere | 7.50 | - | - | 10.1s | 2025-03-13 | ||
| 177 | Command-R (Mar '24) | Cohere | 1.70 | - | - | - | 2024-03-12 | ||
| 178 | Command-R+ (Apr '24) | Cohere | 2.60 | - | - | - | 2024-04-04 | ||
| 179 | DBRX Instruct | Databricks | 2.60 | - | - | - | 2024-03-27 | ||
| 180 | DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research | 1.90 | - | - | - | 2025-02-13 | ||
| 181 | DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 5.00 | - | - | - | 2025-03-13 | ||
| 182 | DeepSeek Coder V2 Lite Instruct | DeepSeek | 2.70 | - | - | - | 2024-06-17 | ||
| 183 | DeepSeek LLM 67B Chat (V1) | DeepSeek | 2.60 | - | - | - | 2023-11-29 | ||
| 184 | DeepSeek R1 0528 (May '25) | DeepSeek | 20.40 | - | - | - | 2025-05-28 | ||
| 185 | DeepSeek R1 0528 Qwen3 8B | DeepSeek | 10.30 | - | - | - | 2025-05-29 | ||
| 186 | DeepSeek R1 Distill Llama 70B | DeepSeek | 9.80 | - | - | 100.1s | 2025-01-20 | ||
| 187 | DeepSeek R1 Distill Llama 8B | DeepSeek | 6.20 | - | - | - | 2025-01-20 | ||
| 188 | DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 3.30 | - | - | - | 2025-01-20 | ||
| 189 | DeepSeek R1 Distill Qwen 14B | DeepSeek | 9.70 | - | - | - | 2025-01-20 | ||
| 190 | DeepSeek R1 Distill Qwen 32B | DeepSeek | 11.00 | - | - | - | 2025-01-20 | ||
| 191 | DeepSeek V3.1 (Non-reasoning) | DeepSeek | 21.40 | - | - | - | 2025-08-21 | ||
| 192 | DeepSeek V3.1 (Reasoning) | DeepSeek | 21.00 | - | - | - | 2025-08-21 | ||
| 193 | DeepSeek V3.1 Terminus (Non-reasoning) | DeepSeek | 21.70 | - | - | - | 2025-09-22 | ||
| 194 | DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 31.40 | - | - | - | 2025-09-22 | ||
| 195 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | 25.10 | - | - | - | 2025-12-01 | ||
| 196 | DeepSeek V3.2 (Reasoning) | DeepSeek | 32.80 | - | - | - | 2025-12-01 | ||
| 197 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | 21.70 | - | - | - | 2025-09-29 | ||
| 198 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | 25.90 | - | - | - | 2025-09-29 | ||
| 199 | DeepSeek V3.2 Speciale | DeepSeek | 22.60 | - | - | - | 2025-12-01 | ||
| 200 | DeepSeek V4 Flash (Non-reasoning) | DeepSeek | 29.30 | - | - | - | 2026-04-24 | ||
| 201 | DeepSeek V4 Pro (Non-reasoning) | DeepSeek | 31.90 | - | - | 8.37s | 2026-04-24 | ||
| 202 | DeepSeek-Coder-V2 | DeepSeek | 4.70 | - | - | - | 2024-06-17 | ||
| 203 | DeepSeek-V2-Chat | DeepSeek | 3.30 | - | - | - | 2024-05-06 | ||
| 204 | DeepSeek-V2.5 | DeepSeek | 6.40 | - | - | - | 2024-09-06 | ||
| 205 | DeepSeek-V2.5 (Dec '24) | DeepSeek | 6.50 | - | - | - | 2024-12-10 | ||
| 206 | Devstral Medium | Mistral | 12.40 | - | - | - | 2025-07-10 | ||
| 207 | Devstral Small (Jul '25) | Mistral | 9.10 | - | - | - | 2025-07-10 | ||
| 208 | Devstral Small (May '25) | Mistral | 11.80 | - | - | - | 2025-05-21 | ||
| 209 | DiffusionGemma 26B A4B | 13.50 | - | - | - | 2026-06-10 | |||
| 210 | Doubao Seed Code | ByteDance Seed | 26.50 | - | - | - | 2025-11-11 | ||
| 211 | ERNIE 4.5 300B A47B | Baidu | 8.90 | - | - | - | 2025-06-30 | ||
| 212 | ERNIE 5.0 Thinking Preview | Baidu | 22.30 | - | - | - | 2025-11-13 | ||
| 213 | Exaone 4.0 1.2B (Non-reasoning) | LG AI Research | 2.40 | - | - | - | 2025-07-15 | ||
| 214 | Exaone 4.0 1.2B (Reasoning) | LG AI Research | 2.50 | - | - | - | 2025-07-15 | ||
| 215 | EXAONE 4.0 32B (Non-reasoning) | LG AI Research | 5.70 | - | - | - | 2025-07-15 | ||
| 216 | EXAONE 4.0 32B (Reasoning) | LG AI Research | 10.50 | - | - | - | 2025-07-15 | ||
| 217 | EXAONE 4.5 33B | LG AI Research | 20.50 | - | - | - | 2026-04-09 | ||
| 218 | EXAONE 4.5 33B (Non-reasoning) | LG AI Research | - | - | - | - | 2026-04-09 | ||
| 219 | Falcon-H1R-7B | TII UAE | 9.70 | - | - | - | 2026-01-04 | ||
| 220 | G9v3-39A5B | AI9Stars | 31.60 | - | - | - | 2026-08-03 | ||
| 221 | G9v3-3B | AI9Stars | 16.20 | - | - | - | 2026-07-23 | ||
| 222 | Gemini 1.0 Pro | 2.70 | - | - | - | 2023-12-06 | |||
| 223 | Gemini 1.0 Ultra | 4.30 | - | - | - | 2023-12-06 | |||
| 224 | Gemini 1.5 Flash (May '24) | 4.60 | - | - | - | 2024-05-14 | |||
| 225 | Gemini 1.5 Flash (Sep '24) | 7.80 | - | - | - | 2024-09-24 | |||
| 226 | Gemini 1.5 Flash-8B | 5.20 | - | - | - | 2024-10-03 | |||
| 227 | Gemini 1.5 Pro (May '24) | 6.10 | - | - | - | 2024-05-15 | |||
| 228 | Gemini 1.5 Pro (Sep '24) | 9.90 | - | - | - | 2024-09-24 | |||
| 229 | Gemini 2.0 Flash (experimental) | 10.60 | - | - | - | 2024-12-11 | |||
| 230 | Gemini 2.0 Flash (Feb '25) | 12.20 | - | - | - | 2025-02-05 | |||
| 231 | Gemini 2.0 Flash Thinking Experimental (Dec '24) | 6.40 | - | - | - | 2024-12-19 | |||
| 232 | Gemini 2.0 Flash Thinking Experimental (Jan '25) | 13.30 | - | - | - | 2025-01-21 | |||
| 233 | Gemini 2.0 Flash-Lite (Feb '25) | 8.60 | - | - | - | 2025-02-25 | |||
| 234 | Gemini 2.0 Flash-Lite (Preview) | 8.40 | - | - | - | 2025-02-05 | |||
| 235 | Gemini 2.0 Pro Experimental (Feb '25) | 11.80 | - | - | - | 2025-02-05 | |||
| 236 | Gemini 2.5 Flash (Non-reasoning) | 14.20 | - | - | 2.96s | 2025-05-20 | |||
| 237 | Gemini 2.5 Flash (Reasoning) | 20.30 | - | - | 21.3s | 2025-05-20 | |||
| 238 | Gemini 2.5 Flash Preview (Non-reasoning) | 11.60 | - | - | - | 2025-04-17 | |||
| 239 | Gemini 2.5 Flash Preview (Reasoning) | 17.70 | - | - | - | 2025-04-17 | |||
| 240 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 19.10 | - | - | - | 2025-09-25 | |||
| 241 | Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 24.20 | - | - | - | 2025-09-25 | |||
| 242 | Gemini 2.5 Flash-Lite (Non-reasoning) | 6.70 | - | - | 2.47s | 2025-06-17 | |||
| 243 | Gemini 2.5 Flash-Lite (Reasoning) | 11.40 | - | - | 26.2s | 2025-06-17 | |||
| 244 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 13.10 | - | - | - | 2025-09-25 | |||
| 245 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 15.20 | - | - | - | 2025-09-08 | |||
| 246 | Gemini 2.5 Pro Preview (Mar' 25) | 23.40 | - | - | - | 2025-03-25 | |||
| 247 | Gemini 2.5 Pro Preview (May' 25) | 22.70 | - | - | - | 2025-05-06 | |||
| 248 | Gemini 3 Deep Think | - | - | - | - | 2026-02-05 | |||
| 249 | Gemini 3 Flash Preview (Non-reasoning) | 27.90 | - | - | 3.70s | 2025-12-17 | |||
| 250 | Gemini 3 Flash Preview (Reasoning) | 38.70 | - | - | 9.32s | 2025-12-17 | |||
| 251 | Gemini 3 Pro Preview (high) | 40.60 | - | - | - | 2025-11-18 | |||
| 252 | Gemini 3 Pro Preview (low) | 33.90 | - | - | - | 2025-11-18 | |||
| 253 | Gemini 3.5 Flash (medium) | 46.70 | - | - | 23.5s | 2026-05-19 | |||
| 254 | Gemini 3.5 Flash (minimal) | 35.80 | - | - | 4.06s | 2026-05-19 | |||
| 255 | Gemma 3 1B Instruct | 1.00 | - | - | - | 2025-03-13 | |||
| 256 | Gemma 3 270M | 2.00 | - | - | - | 2025-08-14 | |||
| 257 | Gemma 3 4B Instruct | 1.00 | - | - | - | 2025-03-12 | |||
| 258 | Gemma 3n E2B Instruct | 1.00 | - | - | - | 2025-06-26 | |||
| 259 | Gemma 3n E4B Instruct | 1.00 | - | - | 10.5s | 2025-06-26 | |||
| 260 | Gemma 3n E4B Instruct Preview (May '25) | 4.20 | - | - | - | 2025-05-20 | |||
| 261 | Gemma 4 12B (Non-reasoning) | 13.20 | - | - | 6.70s | 2026-06-03 | |||
| 262 | Gemma 4 12B (Reasoning) | 22.20 | - | - | 25.2s | 2026-06-03 | |||
| 263 | Gemma 4 26B A4B (Non-reasoning) | 20.40 | - | - | 7.77s | 2026-04-02 | |||
| 264 | Gemma 4 E2B (Non-reasoning) | 6.20 | - | - | - | 2026-04-02 | |||
| 265 | Gemma 4 E2B (Reasoning) | 9.50 | - | - | - | 2026-04-02 | |||
| 266 | Gemma 4 E4B (Non-reasoning) | 8.70 | - | - | 10.6s | 2026-04-03 | |||
| 267 | Gemma 4 E4B (Reasoning) | 12.20 | - | - | 46.8s | 2026-04-03 | |||
| 268 | GLM 5V Turbo (Reasoning) | Z AI | 35.30 | - | - | - | 2026-04-01 | ||
| 269 | GLM-4.5 (Reasoning) | Z AI | 19.70 | - | - | - | 2025-07-28 | ||
| 270 | GLM-4.5-Air | Z AI | 16.70 | - | - | 34.9s | 2025-07-28 | ||
| 271 | GLM-4.5V (Non-reasoning) | Z AI | 6.80 | - | - | 7.26s | 2025-08-11 | ||
| 272 | GLM-4.5V (Reasoning) | Z AI | 9.00 | - | - | 31.7s | 2025-08-11 | ||
| 273 | GLM-4.6 (Non-reasoning) | Z AI | 23.40 | - | - | 11.8s | 2025-09-30 | ||
| 274 | GLM-4.6V (Non-reasoning) | Z AI | 10.90 | - | - | 10.6s | 2025-12-08 | ||
| 275 | GLM-4.6V (Reasoning) | Z AI | 16.90 | - | - | 39.1s | 2025-12-08 | ||
| 276 | GLM-4.7 (Non-reasoning) | Z AI | 27.10 | - | - | 5.90s | 2025-12-22 | ||
| 277 | GLM-4.7-Flash (Non-reasoning) | Z AI | 15.60 | - | - | 6.34s | 2026-01-19 | ||
| 278 | GLM-4.7-Flash (Reasoning) | Z AI | 23.30 | - | - | 28.0s | 2026-01-19 | ||
| 279 | GLM-5 (Non-reasoning) | Z AI | 33.20 | - | - | 14.2s | 2026-02-11 | ||
| 280 | GLM-5 (Reasoning) | Z AI | 40.60 | - | - | 80.3s | 2026-02-11 | ||
| 281 | GLM-5-Turbo | Z AI | 39.10 | - | - | - | 2026-03-15 | ||
| 282 | GLM-5.1 (Non-reasoning) | Z AI | 36.30 | - | - | 9.83s | 2026-04-07 | ||
| 283 | GLM-5.2 (Non-reasoning) | Z AI | 34.80 | - | - | 5.71s | 2026-06-16 | ||
| 284 | GPT-3.5 Turbo | OpenAI | 3.20 | - | - | - | 2022-11-30 | ||
| 285 | GPT-3.5 Turbo (0613) | OpenAI | - | - | - | - | 2023-06-13 | ||
| 286 | GPT-4 | OpenAI | 6.80 | - | - | - | 2023-03-14 | ||
| 287 | GPT-4 Turbo | OpenAI | 7.70 | - | - | 18.3s | 2023-11-06 | ||
| 288 | GPT-4.1 | OpenAI | 19.60 | - | - | 4.40s | 2025-04-14 | ||
| 289 | GPT-4.5 (Preview) | OpenAI | 13.60 | - | - | - | 2025-02-27 | ||
| 290 | GPT-4o (Aug '24) | OpenAI | 9.40 | - | - | 6.74s | 2024-08-06 | ||
| 291 | GPT-4o (ChatGPT) | OpenAI | 8.10 | - | - | - | 2025-02-15 | ||
| 292 | GPT-4o (March 2025, chatgpt-4o-latest) | OpenAI | 12.30 | - | - | - | 2025-03-27 | ||
| 293 | GPT-4o (May '24) | OpenAI | 8.40 | - | - | 6.73s | 2024-05-13 | ||
| 294 | GPT-4o (Nov '24) | OpenAI | 11.10 | - | - | 4.81s | 2024-11-20 | ||
| 295 | GPT-4o mini | OpenAI | 6.70 | - | - | 5.96s | 2024-07-18 | ||
| 296 | GPT-4o mini Realtime (Dec '24) | OpenAI | - | - | - | - | 2024-12-17 | ||
| 297 | GPT-4o Realtime (Dec '24) | OpenAI | - | - | - | - | 2024-12-17 | ||
| 298 | GPT-5 (ChatGPT) | OpenAI | 15.40 | - | - | - | 2025-08-07 | ||
| 299 | GPT-5 (low) | OpenAI | 31.90 | - | - | 18.3s | 2025-08-07 | ||
| 300 | GPT-5 (medium) | OpenAI | 34.60 | - | - | 42.9s | 2025-08-07 | ||
| 301 | GPT-5 (minimal) | OpenAI | 17.30 | - | - | 7.78s | 2025-08-07 | ||
| 302 | GPT-5 Codex (high) | OpenAI | 37.00 | - | - | - | 2025-09-23 | ||
| 303 | GPT-5 mini (medium) | OpenAI | 31.60 | - | - | 18.8s | 2025-08-07 | ||
| 304 | GPT-5 mini (minimal) | OpenAI | 14.30 | - | - | 6.24s | 2025-08-07 | ||
| 305 | GPT-5 nano (high) | OpenAI | 20.10 | - | - | 97.3s | 2025-08-07 | ||
| 306 | GPT-5 nano (medium) | OpenAI | 19.20 | - | - | 50.0s | 2025-08-07 | ||
| 307 | GPT-5 nano (minimal) | OpenAI | 7.80 | - | - | 3.96s | 2025-08-07 | ||
| 308 | GPT-5.1 (Non-reasoning) | OpenAI | 20.70 | - | - | 6.18s | 2025-11-13 | ||
| 309 | GPT-5.1 Codex (high) | OpenAI | 35.60 | - | - | - | 2025-11-13 | ||
| 310 | GPT-5.1 Codex mini (high) | OpenAI | 31.30 | - | - | - | 2025-11-13 | ||
| 311 | GPT-5.2 (medium) | OpenAI | 38.90 | - | - | - | 2025-12-11 | ||
| 312 | GPT-5.2 (Non-reasoning) | OpenAI | 26.50 | - | - | 8.39s | 2025-12-11 | ||
| 313 | GPT-5.2 (xhigh) | OpenAI | 43.30 | - | - | 149.3s | 2025-12-11 | ||
| 314 | GPT-5.2 Codex (xhigh) | OpenAI | 41.20 | - | - | - | 2025-12-11 | ||
| 315 | GPT-5.3 Codex (xhigh) | OpenAI | 45.50 | - | - | 78.6s | 2026-02-05 | ||
| 316 | GPT-5.4 (low) | OpenAI | 40.20 | - | - | 7.04s | 2026-03-05 | ||
| 317 | GPT-5.4 (Non-reasoning) | OpenAI | 28.30 | - | - | 6.35s | 2026-03-05 | ||
| 318 | GPT-5.4 mini (medium) | OpenAI | 30.50 | - | - | 11.3s | 2026-03-17 | ||
| 319 | GPT-5.4 mini (Non-Reasoning) | OpenAI | 16.80 | - | - | 3.80s | 2026-03-17 | ||
| 320 | GPT-5.4 nano (medium) | OpenAI | 30.80 | - | - | 7.15s | 2026-03-17 | ||
| 321 | GPT-5.4 nano (Non-Reasoning) | OpenAI | 17.80 | - | - | 3.61s | 2026-03-17 | ||
| 322 | GPT-5.4 Pro (xhigh) | OpenAI | - | - | - | - | 2026-03-05 | ||
| 323 | GPT-5.5 Instant (May 2026) | OpenAI | 34.30 | - | - | - | 2026-05-05 | ||
| 324 | GPT-5.5 Pro (xhigh) | OpenAI | - | - | - | - | 2026-04-23 | ||
| 325 | gpt-oss-20b (low) | OpenAI | 14.40 | - | - | 15.8s | 2025-08-05 | ||
| 326 | Granite 3.3 8B (Non-reasoning) | IBM | 1.30 | - | - | 63.2s | 2025-04-16 | ||
| 327 | Granite 4.0 1B | IBM | 1.60 | - | - | - | 2025-10-28 | ||
| 328 | Granite 4.0 350M | IBM | 1.00 | - | - | - | 2025-10-28 | ||
| 329 | Granite 4.0 H 1B | IBM | 2.20 | - | - | - | 2025-10-28 | ||
| 330 | Granite 4.0 H 350M | IBM | 1.00 | - | - | - | 2025-10-28 | ||
| 331 | Granite 4.0 H Small | IBM | 4.90 | - | - | 38.9s | 2025-09-22 | ||
| 332 | Granite 4.0 Micro | IBM | 2.00 | - | - | - | 2025-09-22 | ||
| 333 | Granite 4.1 30B | IBM | 8.70 | - | - | - | 2026-04-29 | ||
| 334 | Granite 4.1 3B | IBM | 4.40 | - | - | - | 2026-04-29 | ||
| 335 | Granite 4.1 8B | IBM | 6.40 | - | - | 5.11s | 2026-04-29 | ||
| 336 | Grok 2 (Dec '24) | SpaceXAI | 7.80 | - | - | - | 2024-12-12 | ||
| 337 | Grok 3 | SpaceXAI | 18.60 | - | - | - | 2025-02-19 | ||
| 338 | Grok 3 mini Reasoning (high) | SpaceXAI | 22.90 | - | - | 35.5s | 2025-02-19 | ||
| 339 | Grok 3 Reasoning Beta | SpaceXAI | 15.20 | - | - | - | 2025-02-19 | ||
| 340 | Grok 4 | SpaceXAI | 34.10 | - | - | - | 2025-07-10 | ||
| 341 | Grok 4 Fast (Non-reasoning) | SpaceXAI | 16.60 | - | - | - | 2025-09-19 | ||
| 342 | Grok 4 Fast (Reasoning) | SpaceXAI | 27.90 | - | - | - | 2025-09-19 | ||
| 343 | Grok 4.1 Fast (Non-reasoning) | SpaceXAI | 17.00 | - | - | - | 2025-11-19 | ||
| 344 | Grok 4.1 Fast (Reasoning) | SpaceXAI | 31.30 | - | - | - | 2025-11-19 | ||
| 345 | Grok 4.20 0309 (Non-reasoning) | SpaceXAI | 22.90 | - | - | - | 2026-03-10 | ||
| 346 | Grok 4.20 0309 (Reasoning) | SpaceXAI | 37.40 | - | - | - | 2026-03-10 | ||
| 347 | Grok 4.20 0309 v2 (Non-reasoning) | SpaceXAI | 22.20 | - | - | 6.50s | 2026-04-07 | ||
| 348 | Grok 4.20 0309 v2 (Reasoning) | SpaceXAI | 38.00 | - | - | 27.4s | 2026-04-07 | ||
| 349 | Grok 4.3 (low) | SpaceXAI | 36.30 | - | - | 11.6s | 2026-04-30 | ||
| 350 | Grok 4.3 (medium) | SpaceXAI | 36.90 | - | - | 17.9s | 2026-04-30 | ||
| 351 | Grok Beta | SpaceXAI | 7.30 | - | - | - | 2024-08-13 | ||
| 352 | Grok Code Fast 1 | SpaceXAI | 22.00 | - | - | - | 2025-08-28 | ||
| 353 | Grok-1 | SpaceXAI | 5.80 | - | - | - | 2024-03-17 | ||
| 354 | Hermes 3 - Llama-3.1 70B | Nous Research | 4.80 | - | - | 16.6s | 2024-08-15 | ||
| 355 | Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 8.60 | - | - | 25.6s | 2025-08-27 | ||
| 356 | Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 8.80 | - | - | 86.2s | 2025-08-27 | ||
| 357 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 6.70 | - | - | 10.4s | 2025-08-27 | ||
| 358 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 9.90 | - | - | 35.4s | 2025-08-27 | ||
| 359 | Hy3-preview (Non-reasoning) | Tencent | 26.60 | - | - | - | 2026-04-23 | ||
| 360 | Hy3-preview (Reasoning) | Tencent | 34.40 | - | - | - | 2026-04-23 | ||
| 361 | HyperCLOVA X SEED Think (32B) | Naver | 17.20 | - | - | - | 2025-12-26 | ||
| 362 | HyperNova 60B 2605 | Multiverse Computing | 18.30 | - | - | - | 2026-05-26 | ||
| 363 | INTELLECT-3 | Prime Intellect | 15.70 | - | - | - | 2025-11-27 | ||
| 364 | Jamba 1.5 Large | AI21 Labs | 4.80 | - | - | - | 2024-08-22 | ||
| 365 | Jamba 1.5 Mini | AI21 Labs | 2.30 | - | - | - | 2024-08-22 | ||
| 366 | Jamba 1.6 Large | AI21 Labs | 4.70 | - | - | - | 2025-03-06 | ||
| 367 | Jamba 1.6 Mini | AI21 Labs | 2.10 | - | - | - | 2025-03-06 | ||
| 368 | Jamba 1.7 Large | AI21 Labs | 5.00 | - | - | - | 2025-07-07 | ||
| 369 | Jamba 1.7 Mini | AI21 Labs | 2.30 | - | - | - | 2025-07-07 | ||
| 370 | Jamba Reasoning 3B | AI21 Labs | 3.80 | - | - | - | 2025-10-08 | ||
| 371 | JT-35B-Flash | China Mobile | 29.00 | - | - | - | 2026-05-14 | ||
| 372 | JT-4.1 Flash 236B A21B | China Mobile | 39.90 | - | - | - | 2026-07-09 | ||
| 373 | JT-MINI | China Mobile | 18.80 | - | - | - | 2026-04-15 | ||
| 374 | K-EXAONE (Non-reasoning) | LG AI Research | 16.90 | - | - | - | 2025-12-31 | ||
| 375 | K-EXAONE (Reasoning) | LG AI Research | 22.50 | - | - | - | 2025-12-31 | ||
| 376 | K-EXAONE 2.0 0803 | LG AI Research | 31.00 | - | - | - | 2026-08-12 | ||
| 377 | K2 Think V2 | Foundation Models的MBZUAI Institute | 17.40 | - | - | - | 2025-12-15 | ||
| 378 | K2-V2 (high) | Foundation Models的MBZUAI Institute | 14.20 | - | - | - | 2025-12-05 | ||
| 379 | K2-V2 (low) | Foundation Models的MBZUAI Institute | 8.40 | - | - | - | 2025-12-05 | ||
| 380 | K2-V2 (medium) | Foundation Models的MBZUAI Institute | 12.40 | - | - | - | 2025-12-05 | ||
| 381 | KAT Coder Pro V2 | KwaiKAT | 33.70 | - | - | 6.04s | 2026-03-27 | ||
| 382 | KAT-Coder-Pro V1 | KwaiKAT | 28.90 | - | - | - | 2025-11-11 | ||
| 383 | Kimi K2 | Kimi | 19.70 | - | - | 13.4s | 2025-07-11 | ||
| 384 | Kimi K2 0905 | Kimi | 24.00 | - | - | 13.4s | 2025-09-05 | ||
| 385 | Kimi K2 Thinking | Kimi | 33.50 | - | - | 22.0s | 2025-11-06 | ||
| 386 | Kimi K2.5 (Non-reasoning) | Kimi | 30.10 | - | - | 14.0s | 2026-01-27 | ||
| 387 | Kimi K2.6 (Non-reasoning) | Kimi | 35.40 | - | - | 15.3s | 2026-04-20 | ||
| 388 | Kimi Linear 48B A3B Instruct | Kimi | 8.40 | - | - | - | 2025-10-30 | ||
| 389 | LFM 40B | Liquid AI | 3.00 | - | - | - | 2024-09-30 | ||
| 390 | LFM2 1.2B | Liquid AI | 1.00 | - | - | - | 2025-07-10 | ||
| 391 | LFM2 2.6B | Liquid AI | 2.30 | - | - | - | 2025-09-23 | ||
| 392 | LFM2 24B A2B | Liquid AI | 4.60 | - | - | - | 2026-02-25 | ||
| 393 | LFM2 8B A1B | Liquid AI | 1.30 | - | - | - | 2025-10-07 | ||
| 394 | LFM2.5-1.2B-Instruct | Liquid AI | 2.30 | - | - | - | 2026-01-05 | ||
| 395 | LFM2.5-1.2B-Thinking | Liquid AI | 2.30 | - | - | - | 2026-01-20 | ||
| 396 | LFM2.5-8B-A1B | Liquid AI | 8.10 | - | - | 9.34s | 2026-05-28 | ||
| 397 | LFM2.5-VL-1.6B | Liquid AI | 1.00 | - | - | 4.20s | 2026-01-05 | ||
| 398 | Ling 2.6 Flash | InclusionAI | 14.20 | - | - | 6.59s | 2026-04-21 | ||
| 399 | Ling-1T | InclusionAI | 12.70 | - | - | - | 2025-10-08 | ||
| 400 | Ling-2.6-1T | InclusionAI | 26.60 | - | - | - | 2026-04-23 | ||
| 401 | Ling-flash-2.0 | InclusionAI | 9.60 | - | - | 8.21s | 2025-09-17 | ||
| 402 | Ling-mini-2.0 | InclusionAI | 3.40 | - | - | - | 2025-09-09 | ||
| 403 | Llama 2 Chat 13B | Meta | 2.60 | - | - | - | 2023-07-18 | ||
| 404 | Llama 2 Chat 70B | Meta | 2.60 | - | - | - | 2023-07-18 | ||
| 405 | Llama 2 Chat 7B | Meta | 3.90 | - | - | - | 2023-07-18 | ||
| 406 | Llama 3 Instruct 70B | Meta | 3.10 | - | - | - | 2024-04-18 | ||
| 407 | Llama 3 Instruct 8B | Meta | 1.00 | - | - | - | 2024-04-18 | ||
| 408 | Llama 3.1 Instruct 405B | Meta | 8.30 | - | - | - | 2024-07-23 | ||
| 409 | Llama 3.1 Instruct 70B | Meta | 6.50 | - | - | 10.4s | 2024-07-23 | ||
| 410 | Llama 3.1 Instruct 8B | Meta | 7.40 | - | - | 4.58s | 2024-07-23 | ||
| 411 | Llama 3.1 Nemotron Instruct 70B | NVIDIA | 7.40 | - | - | 10.0s | 2024-10-15 | ||
| 412 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 8.40 | - | - | - | 2025-05-20 | ||
| 413 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 8.90 | - | - | 54.4s | 2025-04-07 | ||
| 414 | Llama 3.1 Tulu3 405B | Allen Institute for AI | 8.10 | - | - | - | 2025-01-30 | ||
| 415 | Llama 3.2 Instruct 11B (Vision) | Meta | 3.00 | - | - | 11.7s | 2024-09-25 | ||
| 416 | Llama 3.2 Instruct 1B | Meta | 1.00 | - | - | - | 2024-09-25 | ||
| 417 | Llama 3.2 Instruct 3B | Meta | 3.90 | - | - | - | 2024-09-25 | ||
| 418 | Llama 3.2 Instruct 90B (Vision) | Meta | 6.00 | - | - | - | 2024-09-25 | ||
| 419 | Llama 3.3 Instruct 70B | Meta | 9.30 | - | - | 7.32s | 2024-12-06 | ||
| 420 | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | NVIDIA | 8.30 | - | - | - | 2025-03-18 | ||
| 421 | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | NVIDIA | 12.20 | - | - | - | 2025-03-18 | ||
| 422 | Llama 65B | Meta | 1.70 | - | - | - | 2023-02-24 | ||
| 423 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 8.50 | - | - | 12.5s | 2025-07-25 | ||
| 424 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | 12.40 | - | - | 27.9s | 2025-07-25 | ||
| 425 | LongCat Flash Lite | LongCat | 17.40 | - | - | - | 2026-01-28 | ||
| 426 | Magistral Medium 1 | Mistral | 12.50 | - | - | - | 2025-06-10 | ||
| 427 | Magistral Small 1 | Mistral | 10.60 | - | - | - | 2025-06-10 | ||
| 428 | Mi:dm K 2.5 Pro | Korea Telecom | 16.60 | - | - | - | 2025-12-11 | ||
| 429 | Mi:dm K 2.5 Pro Preview | Korea Telecom | - | - | - | - | 2025-12-11 | ||
| 430 | MiMo-V2-Flash (Feb 2026) | Xiaomi | 34.00 | - | - | - | 2025-12-16 | ||
| 431 | MiMo-V2-Flash (Non-reasoning) | Xiaomi | 25.10 | - | - | - | 2025-12-16 | ||
| 432 | MiMo-V2-Flash (Reasoning) | Xiaomi | 31.90 | - | - | - | 2025-12-16 | ||
| 433 | MiMo-V2-Omni | Xiaomi | 35.90 | - | - | - | 2026-03-19 | ||
| 434 | MiMo-V2-Omni-0327 | Xiaomi | 37.30 | - | - | - | 2026-03-27 | ||
| 435 | MiMo-V2-Pro | Xiaomi | 41.40 | - | - | - | 2026-03-18 | ||
| 436 | MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 28.40 | - | - | 11.8s | 2026-04-22 | ||
| 437 | MiniCPM-V 4.6 1.3B | OpenBMB | 3.80 | - | - | - | 2026-05-11 | ||
| 438 | MiniCPM5-1B (Non-reasoning) | OpenBMB | 11.70 | - | - | - | 2026-05-25 | ||
| 439 | MiniCPM5-1B (Reasoning) | OpenBMB | 11.90 | - | - | - | 2026-05-25 | ||
| 440 | MiniMax M1 40k | MiniMax | 14.50 | - | - | - | 2025-06-17 | ||
| 441 | MiniMax M1 80k | MiniMax | 17.90 | - | - | - | 2025-06-17 | ||
| 442 | MiniMax-M2 | MiniMax | 28.90 | - | - | 29.7s | 2025-10-26 | ||
| 443 | MiniMax-M2.1 | MiniMax | 32.10 | - | - | 30.2s | 2025-12-23 | ||
| 444 | MiniMax-M2.5 | MiniMax | 34.50 | - | - | 28.1s | 2026-02-12 | ||
| 445 | Mistral 7B Instruct | Mistral | 1.70 | - | - | 4.87s | 2023-09-27 | ||
| 446 | Mistral Large (Feb '24) | Mistral | 4.10 | - | - | - | 2024-02-26 | ||
| 447 | Mistral Large 2 (Jul '24) | Mistral | 7.00 | - | - | - | 2024-07-24 | ||
| 448 | Mistral Large 2 (Nov '24) | Mistral | 9.00 | - | - | - | 2024-11-18 | ||
| 449 | Mistral Medium | Mistral | 3.20 | - | - | 5.95s | 2023-12-11 | ||
| 450 | Mistral Medium 3 | Mistral | 12.50 | - | - | 10.3s | 2025-05-07 | ||
| 451 | Mistral Saba | Mistral | 6.20 | - | - | - | 2025-02-17 | ||
| 452 | Mistral Small (Feb '24) | Mistral | 3.20 | - | - | 4.12s | 2024-02-26 | ||
| 453 | Mistral Small (Sep '24) | Mistral | 4.30 | - | - | 4.08s | 2024-09-17 | ||
| 454 | Mistral Small 3 | Mistral | 6.70 | - | - | 4.31s | 2025-01-30 | ||
| 455 | Mistral Small 4 (Non-reasoning) | Mistral | 12.30 | - | - | 4.46s | 2026-03-16 | ||
| 456 | Mixtral 8x22B Instruct | Mistral | 4.00 | - | - | - | 2024-04-17 | ||
| 457 | Mixtral 8x7B Instruct | Mistral | 2.00 | - | - | - | 2023-12-11 | ||
| 458 | Molmo 7B-D | Allen Institute for AI | 3.40 | - | - | - | 2024-09-25 | ||
| 459 | Molmo2-8B | Allen Institute for AI | 1.60 | - | - | - | 2025-12-11 | ||
| 460 | Motif 3 | Motif Technologies | 47.40 | - | - | - | 2026-08-12 | ||
| 461 | Motif 3 (Beta) | Motif Technologies | 45.30 | - | - | - | 2026-07-14 | ||
| 462 | Motif-2-12.7B-Reasoning | Motif Technologies | 12.80 | - | - | - | 2025-12-04 | ||
| 463 | Muse Spark | Meta | 44.30 | - | - | - | 2026-04-08 | ||
| 464 | Nanbeige4.1-3B | Nanbeige | 11.00 | - | - | - | 2026-02-11 | ||
| 465 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 15.00 | - | - | 8.76s | 2026-04-29 | ||
| 466 | Nemotron Cascade 2 30B A3B | NVIDIA | 17.80 | - | - | - | 2026-03-19 | ||
| 467 | Nex-N2-Pro | Nex AGI | 41.70 | - | - | 19.7s | 2026-06-02 | ||
| 468 | Nova 2.0 Lite (high) | Amazon | 20.80 | - | - | 28.6s | 2025-10-29 | ||
| 469 | Nova 2.0 Lite (low) | Amazon | 18.00 | - | - | 22.9s | 2025-10-29 | ||
| 470 | Nova 2.0 Lite (medium) | Amazon | 19.20 | - | - | 34.6s | 2025-10-29 | ||
| 471 | Nova 2.0 Lite (Non-reasoning) | Amazon | 11.80 | - | - | 4.34s | 2025-10-29 | ||
| 472 | Nova 2.0 Omni (low) | Amazon | 16.70 | - | - | - | 2025-11-26 | ||
| 473 | Nova 2.0 Omni (medium) | Amazon | 21.30 | - | - | - | 2025-11-26 | ||
| 474 | Nova 2.0 Omni (Non-reasoning) | Amazon | 10.40 | - | - | - | 2025-11-26 | ||
| 475 | Nova 2.0 Pro Preview (low) | Amazon | 19.80 | - | - | 32.4s | 2025-11-27 | ||
| 476 | Nova 2.0 Pro Preview (medium) | Amazon | 22.10 | - | - | 34.7s | 2025-11-27 | ||
| 477 | Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 14.40 | - | - | 6.19s | 2025-11-27 | ||
| 478 | Nova Lite | Amazon | 6.70 | - | - | 4.16s | 2024-12-03 | ||
| 479 | Nova Micro | Amazon | 4.40 | - | - | 2.64s | 2024-12-03 | ||
| 480 | Nova Premier | Amazon | 12.70 | - | - | 18.0s | 2025-04-30 | ||
| 481 | Nova Pro | Amazon | 7.50 | - | - | - | 2024-12-03 | ||
| 482 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | 7.20 | - | - | 3.12s | 2025-12-15 | ||
| 483 | NVIDIA Nemotron 3 Nano 4B | NVIDIA | 8.60 | - | - | - | 2026-03-16 | ||
| 484 | NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA | 4.20 | - | - | 4.80s | 2025-10-28 | ||
| 485 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA | 8.80 | - | - | 30.6s | 2025-10-28 | ||
| 486 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | 7.20 | - | - | 4.32s | 2025-08-18 | ||
| 487 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 8.70 | - | - | 17.5s | 2025-08-18 | ||
| 488 | o1 | OpenAI | 23.90 | - | - | - | 2024-12-05 | ||
| 489 | o1-mini | OpenAI | 14.00 | - | - | - | 2024-09-12 | ||
| 490 | o1-preview | OpenAI | 17.20 | - | - | - | 2024-09-12 | ||
| 491 | o1-pro | OpenAI | 19.10 | - | - | - | 2025-03-19 | ||
| 492 | o3 | OpenAI | 31.10 | - | - | 12.8s | 2025-04-16 | ||
| 493 | o3-mini | OpenAI | 19.20 | - | - | 8.72s | 2025-01-31 | ||
| 494 | o3-mini (high) | OpenAI | 15.70 | - | - | 23.2s | 2025-01-31 | ||
| 495 | o3-pro | OpenAI | 33.30 | - | - | - | 2025-06-10 | ||
| 496 | o4-mini (high) | OpenAI | 26.10 | - | - | 32.7s | 2025-04-16 | ||
| 497 | OLMo 2 32B | Allen Institute for AI | 4.70 | - | - | - | 2025-03-13 | ||
| 498 | OLMo 2 7B | Allen Institute for AI | 3.50 | - | - | - | 2024-11-26 | ||
| 499 | Olmo 3 32B Think | Allen Institute for AI | 6.10 | - | - | - | 2025-11-20 | ||
| 500 | Olmo 3 7B Instruct | Allen Institute for AI | 2.40 | - | - | - | 2025-11-20 | ||
| 501 | Olmo 3 7B Think | Allen Institute for AI | 3.60 | - | - | - | 2025-11-20 | ||
| 502 | Olmo 3.1 32B Instruct | Allen Institute for AI | 6.20 | - | - | - | 2026-01-13 | ||
| 503 | Olmo 3.1 32B Think | Allen Institute for AI | 7.90 | - | - | - | 2025-12-12 | ||
| 504 | OpenChat 3.5 (1210) | OpenChat | 2.60 | - | - | - | 2023-12-18 | ||
| 505 | PALM-2 | 2.80 | - | - | - | 2023-05-10 | |||
| 506 | Phi-3 Mini Instruct 3.8B | Microsoft | 4.30 | - | - | - | 2024-04-23 | ||
| 507 | Phi-4 | Microsoft | 4.60 | - | - | 15.4s | 2024-12-12 | ||
| 508 | Phi-4 Mini Instruct | Microsoft | 5.70 | - | - | 12.3s | 2024-02-26 | ||
| 509 | Phi-4 Multimodal Instruct | Microsoft | 4.20 | - | - | 29.5s | 2025-02-26 | ||
| 510 | Pixtral Large | Mistral | 8.00 | - | - | - | 2024-11-18 | ||
| 511 | Qwen Chat 14B | Alibaba | 1.70 | - | - | - | 2023-09-25 | ||
| 512 | Qwen Chat 72B | Alibaba | 3.00 | - | - | - | 2023-11-30 | ||
| 513 | Qwen1.5 Chat 110B | Alibaba | 3.70 | - | - | - | 2024-04-25 | ||
| 514 | Qwen2 Instruct 72B | Alibaba | 5.70 | - | - | - | 2024-06-07 | ||
| 515 | Qwen2.5 Coder Instruct 32B | Alibaba | 6.90 | - | - | - | 2024-11-11 | ||
| 516 | Qwen2.5 Coder Instruct 7B | Alibaba | 4.10 | - | - | - | 2024-09-19 | ||
| 517 | Qwen2.5 Instruct 32B | Alibaba | 7.20 | - | - | - | 2024-09-19 | ||
| 518 | Qwen2.5 Instruct 72B | Alibaba | 9.40 | - | - | - | 2024-09-19 | ||
| 519 | Qwen2.5 Max | Alibaba | 10.10 | - | - | - | 2025-01-28 | ||
| 520 | Qwen2.5 Turbo | Alibaba | 6.00 | - | - | 6.80s | 2024-11-18 | ||
| 521 | Qwen3 0.6B (Non-reasoning) | Alibaba | 1.00 | - | - | - | 2025-04-28 | ||
| 522 | Qwen3 0.6B (Reasoning) | Alibaba | 1.00 | - | - | - | 2025-04-28 | ||
| 523 | Qwen3 1.7B (Non-reasoning) | Alibaba | 1.10 | - | - | - | 2025-04-28 | ||
| 524 | Qwen3 1.7B (Reasoning) | Alibaba | 2.20 | - | - | - | 2025-04-28 | ||
| 525 | Qwen3 14B (Non-reasoning) | Alibaba | 6.80 | - | - | 11.1s | 2025-04-28 | ||
| 526 | Qwen3 14B (Reasoning) | Alibaba | 10.40 | - | - | 45.1s | 2025-04-28 | ||
| 527 | Qwen3 235B A22B (Non-reasoning) | Alibaba | 10.80 | - | - | 11.1s | 2025-04-28 | ||
| 528 | Qwen3 235B A22B (Reasoning) | Alibaba | 13.50 | - | - | 43.8s | 2025-04-28 | ||
| 529 | Qwen3 235B A22B 2507 Instruct | Alibaba | 18.40 | - | - | 11.3s | 2025-07-21 | ||
| 530 | Qwen3 30B A3B (Non-reasoning) | Alibaba | 6.60 | - | - | 6.87s | 2025-04-28 | ||
| 531 | Qwen3 30B A3B (Reasoning) | Alibaba | 9.20 | - | - | 26.5s | 2025-04-28 | ||
| 532 | Qwen3 30B A3B 2507 Instruct | Alibaba | 8.90 | - | - | 5.42s | 2025-07-29 | ||
| 533 | Qwen3 32B (Non-reasoning) | Alibaba | 8.50 | - | - | 7.25s | 2025-04-28 | ||
| 534 | Qwen3 32B (Reasoning) | Alibaba | 11.40 | - | - | 27.1s | 2025-04-28 | ||
| 535 | Qwen3 4B (Non-reasoning) | Alibaba | 6.50 | - | - | - | 2025-04-28 | ||
| 536 | Qwen3 4B (Reasoning) | Alibaba | 8.20 | - | - | - | 2025-04-28 | ||
| 537 | Qwen3 4B 2507 (Reasoning) | Alibaba | 11.90 | - | - | - | 2025-08-06 | ||
| 538 | Qwen3 4B 2507 Instruct | Alibaba | 6.90 | - | - | - | 2025-08-06 | ||
| 539 | Qwen3 8B (Non-reasoning) | Alibaba | 4.80 | - | - | 16.6s | 2025-04-28 | ||
| 540 | Qwen3 8B (Reasoning) | Alibaba | 8.30 | - | - | 68.3s | 2025-04-28 | ||
| 541 | Qwen3 Coder 30B A3B Instruct | Alibaba | 13.60 | - | - | 8.03s | 2025-07-31 | ||
| 542 | Qwen3 Coder 480B A35B Instruct | Alibaba | 18.20 | - | - | 10.7s | 2025-07-22 | ||
| 543 | Qwen3 Max | Alibaba | 24.50 | - | - | 11.1s | 2025-09-23 | ||
| 544 | Qwen3 Max (Preview) | Alibaba | 19.40 | - | - | 12.6s | 2025-09-05 | ||
| 545 | Qwen3 Max Thinking | Alibaba | 32.50 | - | - | - | 2026-01-26 | ||
| 546 | Qwen3 Max Thinking (Preview) | Alibaba | 25.50 | - | - | 48.5s | 2025-11-03 | ||
| 547 | Qwen3 Next 80B A3B Instruct | Alibaba | 13.80 | - | - | 4.92s | 2025-09-11 | ||
| 548 | Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 9.50 | - | - | 27.1s | 2025-09-22 | ||
| 549 | Qwen3 Omni 30B A3B Instruct | Alibaba | 4.80 | - | - | 7.38s | 2025-09-22 | ||
| 550 | Qwen3 VL 235B A22B (Reasoning) | Alibaba | 20.90 | - | - | 46.6s | 2025-09-23 | ||
| 551 | Qwen3 VL 235B A22B Instruct | Alibaba | 14.40 | - | - | 13.3s | 2025-09-23 | ||
| 552 | Qwen3 VL 30B A3B (Reasoning) | Alibaba | 13.40 | - | - | 24.7s | 2025-10-03 | ||
| 553 | Qwen3 VL 30B A3B Instruct | Alibaba | 9.90 | - | - | 6.73s | 2025-10-03 | ||
| 554 | Qwen3 VL 32B (Reasoning) | Alibaba | 18.10 | - | - | 30.5s | 2025-10-21 | ||
| 555 | Qwen3 VL 32B Instruct | Alibaba | 11.00 | - | - | 9.95s | 2025-10-21 | ||
| 556 | Qwen3 VL 4B (Reasoning) | Alibaba | 7.70 | - | - | - | 2025-10-14 | ||
| 557 | Qwen3 VL 4B Instruct | Alibaba | 3.70 | - | - | - | 2025-10-14 | ||
| 558 | Qwen3 VL 8B (Reasoning) | Alibaba | 10.50 | - | - | 24.3s | 2025-10-14 | ||
| 559 | Qwen3 VL 8B Instruct | Alibaba | 8.20 | - | - | 6.92s | 2025-10-14 | ||
| 560 | Qwen3.5 0.8B (Non-reasoning) | Alibaba | 2.90 | - | - | - | 2026-03-02 | ||
| 561 | Qwen3.5 0.8B (Reasoning) | Alibaba | 5.20 | - | - | - | 2026-03-02 | ||
| 562 | Qwen3.5 27B (Non-reasoning) | Alibaba | 30.00 | - | - | 11.7s | 2026-02-24 | ||
| 563 | Qwen3.5 27B (Reasoning) | Alibaba | 34.60 | - | - | 37.9s | 2026-02-24 | ||
| 564 | Qwen3.5 2B (Non-reasoning) | Alibaba | 5.30 | - | - | - | 2026-03-02 | ||
| 565 | Qwen3.5 2B (Reasoning) | Alibaba | 7.40 | - | - | - | 2026-03-02 | ||
| 566 | Qwen3.5 35B A3B (Reasoning) | Alibaba | 29.90 | - | - | 18.6s | 2026-02-24 | ||
| 567 | Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 32.70 | - | - | 8.07s | 2026-02-16 | ||
| 568 | Qwen3.5 4B (Non-reasoning) | Alibaba | 16.10 | - | - | 18.3s | 2026-03-02 | ||
| 569 | Qwen3.5 4B (Reasoning) | Alibaba | 20.40 | - | - | 84.4s | 2026-03-02 | ||
| 570 | Qwen3.5 9B (Non-reasoning) | Alibaba | 20.60 | - | - | 6.58s | 2026-03-02 | ||
| 571 | Qwen3.5 Omni Flash | Alibaba | 19.20 | - | - | 3.91s | 2026-03-30 | ||
| 572 | Qwen3.5 Omni Plus | Alibaba | 31.30 | - | - | 12.7s | 2026-03-30 | ||
| 573 | Qwen3.6 Max Preview | Alibaba | 41.10 | - | - | 44.6s | 2026-04-20 | ||
| 574 | Qwen3.8 27B | Alibaba | 52.00 | - | - | - | 2026-08-14 | ||
| 575 | QwQ 32B | Alibaba | 13.40 | - | - | - | 2025-03-05 | ||
| 576 | QwQ 32B-Preview | Alibaba | 9.10 | - | - | - | 2024-11-27 | ||
| 577 | R1 1776 | Perplexity | 6.00 | - | - | - | 2025-02-18 | ||
| 578 | Reka Flash (Sep '24) | Reka AI | 6.00 | - | - | 11.2s | 2024-10-04 | ||
| 579 | Reka Flash 3 | Reka AI | 3.70 | - | - | - | 2025-03-10 | ||
| 580 | Ring-1T | InclusionAI | 16.30 | - | - | - | 2025-10-13 | ||
| 581 | Ring-flash-2.0 | InclusionAI | 8.00 | - | - | - | 2025-09-19 | ||
| 582 | Sarvam 105B (high) | Sarvam | 11.90 | - | - | - | 2026-03-06 | ||
| 583 | Sarvam 30B (high) | Sarvam | 6.40 | - | - | - | 2026-03-06 | ||
| 584 | Sarvam M (Reasoning) | Sarvam | 2.60 | - | - | - | 2025-05-23 | ||
| 585 | Seed-OSS-36B-Instruct | ByteDance Seed | 18.50 | - | - | 87.2s | 2025-08-20 | ||
| 586 | Solar Mini | Upstage | 6.00 | - | - | - | 2024-01-25 | ||
| 587 | Solar Open 100B (Reasoning) | Upstage | 15.20 | - | - | - | 2025-12-17 | ||
| 588 | Solar Open2 250B | Upstage | 37.40 | - | - | - | 2026-08-12 | ||
| 589 | Solar Pro 2 (Non-reasoning) | Upstage | 7.60 | - | - | - | 2025-07-09 | ||
| 590 | Solar Pro 2 (Preview) (Non-reasoning) | Upstage | 9.90 | - | - | - | 2025-05-20 | ||
| 591 | Solar Pro 2 (Preview) (Reasoning) | Upstage | 12.50 | - | - | - | 2025-05-20 | ||
| 592 | Solar Pro 2 (Reasoning) | Upstage | 8.80 | - | - | - | 2025-07-09 | ||
| 593 | Sonar | Perplexity | 9.40 | - | - | - | 2025-01-21 | ||
| 594 | Sonar Pro | Perplexity | 9.10 | - | - | - | 2025-01-21 | ||
| 595 | Sonar Reasoning | Perplexity | 11.60 | - | - | - | 2025-01-28 | ||
| 596 | Sonar Reasoning Pro | Perplexity | 18.00 | - | - | - | 2025-01-28 | ||
| 597 | Step 3.5 Flash | StepFun | 26.00 | - | - | 12.2s | 2026-02-02 | ||
| 598 | Step 3.5 Flash 2603 | StepFun | 26.50 | - | - | 12.8s | 2026-04-02 | ||
| 599 | Step3 VL 10B | StepFun | 9.30 | - | - | - | 2026-01-20 | ||
| 600 | Tiny Aya Global | Cohere | 1.00 | - | - | - | 2026-02-17 | ||
| 601 | Tri-21B-Think | Trillion Labs | 12.30 | - | - | - | 2026-02-10 | ||
| 602 | Tri-21B-think Preview | Trillion Labs | 13.60 | - | - | - | 2026-02-10 |