gpt-oss-120b (High) vs Qwen3 235B A22B 2507 (Reasoning)
Which is better for the money: gpt-oss-120b (High) by OpenAI or Qwen3 235B A22B 2507 (Reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Qwen3 235B A22B 2507 (Reasoning) scores 1.1 points higher (12.7 vs 11.6) but costs 1.9× as much to run the benchmark ($234 vs $123; both mid-range class). Pick Qwen3 235B A22B 2507 (Reasoning) when the extra intelligence is worth the premium, otherwise gpt-oss-120b (High).
| Metric | gpt-oss-120b (High) | Qwen3 235B A22B 2507 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.6 | 12.7 | +9.5% Qwen3 235B A22B 2507 … is 9.5% more intelligent |
| Total AA cost (lower is better) | $122.71 | $233.56 | +90.3% Qwen3 235B A22B 2507 … is 90.3% more expensive |
| End-to-end time (lower is better) | 11.19s | 21.63s | +93.3% Qwen3 235B A22B 2507 … is 93.3% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $0.23 / $2.30 | |
| Input modalities | Text | Text |
Qwen3 235B A22B 2507 (Reasoning) vs gpt-oss-120b (High): 9.5% more intelligence, 90.3% more cost to run the AA benchmark, and 93.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Qwen3 235B A22B 2507 (Reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
gpt-oss-120b (High)Qwen3 235B A22B 2507 (Reasoning)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-oss-120b/qwen3-235b-a22b-instruct-2507-reasoning · Markdown: /api/v1/compare/gpt-oss-120b/qwen3-235b-a22b-instruct-2507-reasoning?format=md · llms.txt · agent skill