Model comparison
o3-mini vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 36.7 on the Noometry Index.
Last verified . 39 shared benchmarks.
Alibaba (Qwen)Summary
- They share 39 benchmarks with published results for both. o3-mini scores higher in 2 categories and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 28.1.
- The biggest single-benchmark swing is MATH Level 5: 96.5% for o3-mini and 68.9% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- o3-mini accepts more context: 200K tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Qwen3 235B-A22B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 43.5 |
| Released | 2024-12-20 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 100K | 16K |
| Input $ / M tokens | $1.10 | $0.70 |
| Output $ / M tokens | $4.40 | $2.80 |
| Results tracked | 51 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
o3-mini: 40.8 (#132), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 60.4% | 59.6% |
| SciCode | 39.8% | 42.4% |
| WeirdML | 43.7% | 41% |
| LMArena Coding | 1378 | 1445 |
| GSO | 1.3% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
o3-mini: 29.6 (#84), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Cybench | 22.5% | — |
| Vending-Bench 2 | — | -11.34 |
Reasoning Too close to call
o3-mini: 16.3 (#305), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 3% | 1.3% |
| SimpleBench | 22.8% | 31% |
| ARC-AGI-1 | 34.5% | 11% |
| CritPt | 0.3% | 0% |
| Chess Puzzles | 17% | 12% |
| LMArena Hard Prompts | 1366 | 1433 |
| Mystery Game Puzzles | 7% | 9% |
| DTBench | 68.8% | 80.3% |
| LMCA | 19% | 29.3% |
| Epoch Capabilities Index | 140.34 | 143.85 |
| ForecastBench | 59.6 | 59.7 |
| Kagi LLM Benchmark | — | 69.4% |
| LiveBench Reasoning | 89.6% | — |
| LiveBench Data Analysis | 70.6% | — |
| LiveBench | 75.9% | — |
Math Qwen3 235B-A22B leads
o3-mini: 28.1 (#244), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 76.9% | 86.7% |
| LMArena Math | 1396 | 1432 |
| MATH Level 5 | 96.5% | 68.9% |
| FrontierMath (Feb 2025 set) | 12.4% | 8.5% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 77.3% | — |
Knowledge Qwen3 235B-A22B leads
o3-mini: 38.3 (#146), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 77% | 80.1% |
| SimpleQA Verified | 15.3% | 40.4% |
| Confabulations | 17.9% | 15.6% |
| LMArena Expert | 1364 | 1463 |
| MMLU-Pro | — | 84.4% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
o3-mini: 45.7 (#164), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1319 | 1409 |
| LMArena Chinese | 1379 | 1481 |
| LMArena French | 1334 | 1445 |
| LMArena German | 1303 | 1433 |
| LMArena Japanese | 1286 | 1399 |
| LMArena Korean | 1314 | 1391 |
| LMArena Russian | 1304 | 1411 |
| LMArena Spanish | 1321 | 1430 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1337 | 1408 |
| LiveBench Instruction Following | 84.4% | — |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
o3-mini: 33.8 (#256), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | 50% | 75% |
| LMArena Longer Query | 1343 | 1426 |
Writing & Preference Qwen3 235B-A22B leads
o3-mini: 50.3 (#182), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | o3-mini | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1337 | 1419 |
| LMArena Creative Writing | 1286 | 1384 |
| Short-Story Creative Writing | 61.7% | 83% |
| LMArena Multi-Turn | 1320 | 1432 |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is o3-mini or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 131K.
How many benchmarks do o3-mini and Qwen3 235B-A22B share?
39 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen3 235B-A22B has 49.