Model comparison
o3-mini vs Qwen2.5 72B Instruct
o3-mini is the stronger model overall, scoring 36.7 to 31.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. o3-mini scores higher in 7 categories and Qwen2.5 72B Instruct in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 27.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 76.9% for o3-mini and 8.1% for Qwen2.5 72B Instruct.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- o3-mini accepts more context: 200K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 31.9 |
| Released | 2024-12-20 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 100K | 8K |
| Input $ / M tokens | $1.10 | $1.40 |
| Output $ / M tokens | $4.40 | $5.60 |
| Results tracked | 51 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 43.7% | 16% |
| LMArena Coding | 1378 | 1292 |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 82.7% | — |
| BigCodeBench Complete | — | 55.9% |
| CadEval | 54% | — |
Agentic & Tool Use o3-mini leads
o3-mini: 29.6 (#84), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| Cybench | 22.5% | — |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
o3-mini: 16.3 (#305), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1366 | 1271 |
| DTBench | 68.8% | 62.9% |
| LMCA | 19% | 13.4% |
| Epoch Capabilities Index | 140.34 | 129 |
| ForecastBench | 59.6 | 57.5 |
| 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% | — |
| LiveBench Data Analysis | 70.6% | — |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| LiveBench | 75.9% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math o3-mini leads
o3-mini: 28.1 (#244), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 76.9% | 8.1% |
| LMArena Math | 1396 | 1283 |
| MATH Level 5 | 96.5% | 63.2% |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | — | 33% |
| 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), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 77% | 49.1% |
| Confabulations | 17.9% | 19.1% |
| LMArena Expert | 1364 | 1245 |
| SimpleQA Verified | 15.3% | — |
| MMLU-Pro | — | 63.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual o3-mini leads
o3-mini: 45.7 (#164), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1319 | 1252 |
| LMArena Chinese | 1379 | 1272 |
| LMArena French | 1334 | 1280 |
| LMArena German | 1303 | 1234 |
| LMArena Japanese | 1286 | 1180 |
| LMArena Korean | 1314 | 1188 |
| LMArena Russian | 1304 | 1264 |
| LMArena Spanish | 1321 | 1256 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1337 | 1254 |
| LiveBench Instruction Following | 84.4% | — |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
o3-mini: 33.8 (#256), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1343 | 1282 |
| Fiction.LiveBench | 50% | — |
Writing & Preference o3-mini leads
o3-mini: 50.3 (#182), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | o3-mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1337 | 1269 |
| LMArena Creative Writing | 1286 | 1221 |
| LMArena Multi-Turn | 1320 | 1272 |
| Short-Story Creative Writing | 61.7% | — |
| WildBench | — | 80.2% |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen2.5 72B Instruct?
o3-mini is the stronger model overall, scoring 36.7 to 31.9 on the Noometry Index.
Which is cheaper, o3-mini or Qwen2.5 72B Instruct?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is o3-mini or Qwen2.5 72B Instruct better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 33.2 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 Qwen2.5 72B Instruct share?
26 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen2.5 72B Instruct has 43.