Model comparison
o3-mini vs Qwen2-72B
o3-mini is the stronger model overall, scoring 36.7 to 30.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. o3-mini scores higher in 6 categories and Qwen2-72B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 21.2.
- The biggest single-benchmark swing is MATH Level 5: 96.5% for o3-mini and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Qwen2-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 30.0 |
| Released | 2024-12-20 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $1.10 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 51 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Qwen2-72B: 29.1 (#310)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| WeirdML | 43.7% | 11.3% |
| LMArena Coding | 1378 | 1196 |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 82.7% | — |
| BigCodeBench Complete | — | 54% |
| CadEval | 54% | — |
Agentic & Tool Use o3-mini leads
o3-mini: 29.6 (#84), Qwen2-72B: 17.0 (#146)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| Cybench | 22.5% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
o3-mini: 16.3 (#305), Qwen2-72B: 23.2 (#181)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1366 | 1191 |
| Epoch Capabilities Index | 140.34 | 125.28 |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 17% | — |
| LiveBench Reasoning | 89.6% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LiveBench Data Analysis | 70.6% | — |
| LMCA | 19% | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Qwen2-72B leads
o3-mini: 28.1 (#244), Qwen2-72B: 30.2 (#236)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Math | 1396 | 1235 |
| MATH Level 5 | 96.5% | 39.1% |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 76.9% | — |
| LiveBench Math | 77.3% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge o3-mini leads
o3-mini: 38.3 (#146), Qwen2-72B: 21.2 (#275)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 77% | 40.8% |
| LMArena Expert | 1364 | 1171 |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
| MMLU | — | 82.4% |
Multilingual o3-mini leads
o3-mini: 45.7 (#164), Qwen2-72B: 35.9 (#244)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1319 | 1176 |
| LMArena Chinese | 1379 | 1240 |
| LMArena French | 1334 | 1170 |
| LMArena German | 1303 | 1151 |
| LMArena Japanese | 1286 | 1111 |
| LMArena Korean | 1314 | 1083 |
| LMArena Russian | 1304 | 1169 |
| LMArena Spanish | 1321 | 1169 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Qwen2-72B: 61.7 (#241)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1337 | 1181 |
| LiveBench Instruction Following | 84.4% | — |
Long Context Qwen2-72B leads
o3-mini: 33.8 (#256), Qwen2-72B: 36.1 (#235)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1343 | 1192 |
| Fiction.LiveBench | 50% | — |
Writing & Preference o3-mini leads
o3-mini: 50.3 (#182), Qwen2-72B: 40.8 (#241)
| Benchmark | o3-mini | Qwen2-72B |
|---|---|---|
| LMArena Text | 1337 | 1203 |
| LMArena Creative Writing | 1286 | 1181 |
| LMArena Multi-Turn | 1320 | 1196 |
| Short-Story Creative Writing | 61.7% | — |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen2-72B?
o3-mini is the stronger model overall, scoring 36.7 to 30.0 on the Noometry Index.
Is o3-mini or Qwen2-72B better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 29.1 in the Noometry coding category.
How many benchmarks do o3-mini and Qwen2-72B share?
21 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen2-72B has 26.