New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
A head-to-head benchmark comparison of DeepSeek-V3.1-Terminus vs Qwen3-235B-A22B-Thinking (Jul 2025) across 34 evaluations. Qwen3-235B-A22B-Thinking (Jul 2025) leads on the most benchmarks (20).
What’s improved? Language consistency: fewer CN/EN mix-ups & no more random chars. Agent upgrades: stronger Code Agent & Search Agent performance. DeepSeek-V.
Full DeepSeek-V3.1-Terminus specs →Today, we are excited to announce the release of Qwen3, the latest addition to the Qwen family of large language models. Our flagship model, Qwen3-235B-A22B, ac.
Full Qwen3-235B-A22B-Thinking (Jul 2025) specs →| Benchmark | DeepSeek-V3.1-Terminus | Qwen3-235B-A22B-Thinking (Jul 2025) |
|---|---|---|
| code | ||
| Codeforces Elo | 2,073 | 2,055 |
| FullStackBench | 55.48% | — |
| LiveCodeBench | 48.02% | 78.2% |
| LiveCodeBench v5 | — | 70.7% |
| LiveCodeBench v6 | 75.33% | 75.72% |
| MBPP | 90.69% | — |
| SciCode | — | 42.9% |
| coding | ||
| Aider Benchmark | 92.86 | 88.91 |
| MultiPL-E | 77.68 | — |
| general | ||
| ArenaHard v2 | 63.24 | 80.18 |
| C-Eval | 91.76% | 93.13% |
| IFEval | 89.09% | 87.8% |
| MMLU-Pro | 85% | 84.5% |
| MMLU-Redux | 92.37% | 92.7% |
| MultiChallenge | 45.79% | 52.75% |
| knowledge | ||
| AGIEval | 89.83 | 90.01 |
| CMMLU | 89.2 | 90.64 |
| TriviaQA | 82.77 | 79.63 |
| math | ||
| AIME 2024 | 71.67% | 94.1% |
| AIME 2025 | 89.06% | 92.3% |
| CNMO 2024 | 85.42% | 89.5% |
| HMMT February 2025 | 86.1% | 83.9% |
| MATH-500 | — | 98% |
| Omni-MATH | 81.93 | 82.52 |
| UGMathBench | 77.19 | 77 |
| reasoning | ||
| ARC-AGI-1 | 40.62 | 48.12 |
| BBEH | 61.04 | 60 |
| FinanceReasoning | 87.76 | 87.65 |
| GPQA Diamond | 81% | 81.1% |
| Humanity's Last Exam | 17.82% | 15.8% |
| ZebraLogic | 96.33% | 97.03% |
| safety | ||
| HealthBench | 50.19% | 55.56% |
| science | ||
| PhyBench | 47.91 | 42.61 |
| tool-use | ||
| BFCL v3 | 62.01% | 73.53% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Across the 34 benchmarks compared here, Qwen3-235B-A22B-Thinking (Jul 2025) leads on the most (20). The right choice still depends on your task — check the per-benchmark table above for coding, reasoning and math.
DeepSeek-V3.1-Terminus has the strongest result on Codeforces Elo among the models compared here. See the code-category rows in the table for the full picture.
This comparison covers 34 benchmarks on which at least one of the selected models has a published score.
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Help us grow the database! Only the announcement link is required — we'll fetch the rest.
Missing a card? Drop the spec/announcement link — we'll verify the specs and add it. The link is the only required field.
Know an inference runtime we're missing (llama.cpp, vLLM, MLX, ComfyUI…)? Drop the link.
Spotted a wrong spec or an out-of-date price? Tell us and we'll verify it.
We'll send you a login code via email
