Model comparison
o4-mini vs Qwen2.5-VL 72B Instruct
o4-mini is the stronger model overall, scoring 41.6 to 29.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. o4-mini scores higher in 3 categories and Qwen2.5-VL 72B Instruct in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o4-mini leads 32.6 to 18.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 67.6% for o4-mini and 36% for Qwen2.5-VL 72B Instruct.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- o4-mini accepts more context: 200K tokens versus 131K.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| o4-mini | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 29.9 |
| Released | 2025-04-16 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 100K | 8K |
| Input $ / M tokens | $1.10 | $2.80 |
| Output $ / M tokens | $4.40 | $8.40 |
| Results tracked | 60 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
o4-mini: 40.9 (#127), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| LMArena Coding | 1368 | — |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use o4-mini leads
o4-mini: 32.6 (#61), Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| OSWorld | — | 5% |
| METR Time Horizons | 63.9% | — |
Reasoning o4-mini leads
o4-mini: 24.6 (#162), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 67.6% | 36% |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| ARC-AGI-1 | 58.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| LMArena Hard Prompts | 1351 | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LMCA | 26.5% | — |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |
Math Not comparable
o4-mini: 40.8 (#89), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| LMArena Math | 1389 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Not comparable
o4-mini: 43.6 (#91), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
| LMArena Expert | 1343 | — |
Multimodal o4-mini leads
o4-mini: 40.2 (#49), Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1194 | 1107 |
| GeoBench | 64% | 62% |
| Video-MME | — | 73.5% |
| VPCT | 57.5% | — |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
o4-mini: 47.0 (#154), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1337 | — |
| LMArena Chinese | 1354 | — |
| LMArena French | 1364 | — |
| LMArena German | 1336 | — |
| LMArena Japanese | 1308 | — |
| LMArena Korean | 1312 | — |
| LMArena Russian | 1334 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Not comparable
o4-mini: 75.2 (#68), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| IFEval | 92.8% | — |
| LMArena Instruction Following | 1321 | — |
Long Context Not comparable
o4-mini: 45.5 (#33), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Fiction.LiveBench | 77.8% | — |
| LMArena Longer Query | 1315 | — |
Writing & Preference Not comparable
o4-mini: 54.0 (#152), Qwen2.5-VL 72B Instruct: —
| Benchmark | o4-mini | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1353 | — |
| LMArena Creative Writing | 1294 | — |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
| LMArena Multi-Turn | 1350 | — |
Frequently asked questions
Is o4-mini better than Qwen2.5-VL 72B Instruct?
o4-mini is the stronger model overall, scoring 41.6 to 29.9 on the Noometry Index.
Which is cheaper, o4-mini or Qwen2.5-VL 72B Instruct?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
o4-mini does, with 200K tokens against 131K.
How many benchmarks do o4-mini and Qwen2.5-VL 72B Instruct share?
3 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.