# o4-mini vs Qwen3-VL 235B-A22B

> Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 41.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o4-mini-vs-qwen3-vl-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. o4-mini scores higher in 5 categories and Qwen3-VL 235B-A22B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-VL 235B-A22B leads 60.2 to 54.0.
- Qwen3-VL 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- o4-mini accepts more context: 200K tokens versus 131K.
- Qwen3-VL 235B-A22B has downloadable open weights; the other is API-only.

## Snapshot

| | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 43.2 |
| Rank | 132 | 95 |
| Context | 200K | 131K |
| Input $/M | $1.10 | $0.70 |
| Output $/M | $4.40 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- o4-mini: 40.9 (#127)
- Qwen3-VL 235B-A22B: 42.4 (#100)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Coding | 1368 | 1439 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |

## Agentic & Tool Use

- o4-mini: 32.6 (#61)
- Qwen3-VL 235B-A22B: —

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |

## Reasoning

- o4-mini: 24.6 (#162)
- Qwen3-VL 235B-A22B: 29.3 (#92)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1351 | 1428 |
| 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% | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LMCA | 26.5% | — |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |

## Math

- o4-mini: 40.8 (#89)
- Qwen3-VL 235B-A22B: 39.0 (#118)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | 1389 | 1426 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |

## Knowledge

- o4-mini: 43.6 (#91)
- Qwen3-VL 235B-A22B: 40.3 (#121)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | 1343 | 1442 |
| 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% | — |

## Multimodal

- o4-mini: 40.2 (#49)
- Qwen3-VL 235B-A22B: 39.8 (#55)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | 1194 | 1247 |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |

## Multilingual

- o4-mini: 47.0 (#154)
- Qwen3-VL 235B-A22B: 51.9 (#97)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | 1337 | 1405 |
| LMArena Chinese | 1354 | 1463 |
| LMArena French | 1364 | 1452 |
| LMArena German | 1336 | 1424 |
| LMArena Japanese | 1308 | 1385 |
| LMArena Korean | 1312 | 1394 |
| LMArena Russian | 1334 | 1408 |
| LMArena Spanish | 1347 | 1428 |

## Instruction Following

- o4-mini: 75.2 (#68)
- Qwen3-VL 235B-A22B: 74.2 (#101)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1406 |
| IFEval | 92.8% | — |

## Long Context

- o4-mini: 45.5 (#33)
- Qwen3-VL 235B-A22B: 43.4 (#98)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1315 | 1420 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- o4-mini: 54.0 (#152)
- Qwen3-VL 235B-A22B: 60.2 (#99)

| Benchmark | o4-mini | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | 1353 | 1420 |
| LMArena Creative Writing | 1294 | 1366 |
| LMArena Multi-Turn | 1350 | 1428 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |

## FAQ

### Is o4-mini better than Qwen3-VL 235B-A22B?

Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 41.6 on the Noometry Index.

### Which is cheaper, o4-mini or Qwen3-VL 235B-A22B?

Qwen3-VL 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; o4-mini lists at $1.10 and $4.40.

### Is o4-mini or Qwen3-VL 235B-A22B better for coding?

Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 40.9 in the Noometry coding category.

### Which has the bigger context window?

o4-mini does, with 200K tokens against 131K.

### How many benchmarks do o4-mini and Qwen3-VL 235B-A22B share?

18 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen3-VL 235B-A22B has 18.