Model comparison
o4-mini vs Qwen2.5-Max
o4-mini and Qwen2.5-Max score almost the same on the Noometry Index (41.6 vs 40.7), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. o4-mini scores higher in 4 categories and Qwen2.5-Max in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.6 to 35.3.
- The biggest single-benchmark swing is Confabulations: 15.8% for o4-mini and 21.8% for Qwen2.5-Max.
Side by side
| o4-mini | Qwen2.5-Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 40.7 |
| Released | 2025-04-16 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $1.10 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
o4-mini: 40.9 (#127), Qwen2.5-Max: 41.8 (#117)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1368 | 1359 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| LiveBench Coding | — | 64.4% |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use Not comparable
o4-mini: 32.6 (#61), Qwen2.5-Max: —
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |
Reasoning Qwen2.5-Max leads
o4-mini: 24.6 (#162), Qwen2.5-Max: 25.6 (#147)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1351 | 1360 |
| Epoch Capabilities Index | 145.64 | 132.53 |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 58.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 26.5% | — |
| ForecastBench | 61.8 | — |
| LiveBench | — | 62.3% |
Math o4-mini leads
o4-mini: 40.8 (#89), Qwen2.5-Max: 36.9 (#162)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1389 | 1369 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge o4-mini leads
o4-mini: 43.6 (#91), Qwen2.5-Max: 35.3 (#186)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| Confabulations | 15.8% | 21.8% |
| LMArena Expert | 1343 | 1337 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Not comparable
o4-mini: 40.2 (#49), Qwen2.5-Max: —
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1194 | — |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual Qwen2.5-Max leads
o4-mini: 47.0 (#154), Qwen2.5-Max: 48.1 (#146)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1337 | 1352 |
| LMArena Chinese | 1354 | 1382 |
| LMArena French | 1364 | 1396 |
| LMArena German | 1336 | 1350 |
| LMArena Japanese | 1308 | 1300 |
| LMArena Korean | 1312 | 1304 |
| LMArena Russian | 1334 | 1353 |
| LMArena Spanish | 1347 | 1377 |
Instruction Following o4-mini leads
o4-mini: 75.2 (#68), Qwen2.5-Max: 71.3 (#152)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1321 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 92.8% | — |
Long Context o4-mini leads
o4-mini: 45.5 (#33), Qwen2.5-Max: 41.4 (#142)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1315 | 1358 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Qwen2.5-Max leads
o4-mini: 54.0 (#152), Qwen2.5-Max: 55.4 (#146)
| Benchmark | o4-mini | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1353 | 1367 |
| LMArena Creative Writing | 1294 | 1339 |
| Short-Story Creative Writing | 75% | 72.9% |
| LMArena Multi-Turn | 1350 | 1364 |
| WildBench | 85.4% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is o4-mini better than Qwen2.5-Max?
o4-mini and Qwen2.5-Max score almost the same on the Noometry Index (41.6 vs 40.7), so choose on price, context window or the category you care about most.
Is o4-mini or Qwen2.5-Max better for coding?
They score almost the same on coding (40.9 vs 41.8); test both on your own repository before choosing.
How many benchmarks do o4-mini and Qwen2.5-Max share?
20 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen2.5-Max has 27.