# o4-mini vs Qwen3.5 122B-A10B

> o4-mini and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.6 vs 42.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/o4-mini-vs-qwen3-5-122b-a10b
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. o4-mini scores higher in 6 categories and Qwen3.5 122B-A10B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.0 to 54.0.
- The biggest single-benchmark swing is Mystery Game Puzzles: 5% for o4-mini and 17% for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B is cheaper at $0.40 / $3.20 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 200K.
- Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

## Snapshot

| | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 42.1 |
| Rank | 132 | 119 |
| Context | 200K | 262K |
| Input $/M | $1.10 | $0.40 |
| Output $/M | $4.40 | $3.20 |
| Weights | Proprietary | Open |

## Coding

- o4-mini: 40.9 (#127)
- Qwen3.5 122B-A10B: 39.1 (#162)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1368 | 1436 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |

## Agentic & Tool Use

- o4-mini: 32.6 (#61)
- Qwen3.5 122B-A10B: —

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |

## Reasoning

- o4-mini: 24.6 (#162)
- Qwen3.5 122B-A10B: 27.2 (#123)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 0.6% | 0.9% |
| LMArena Hard Prompts | 1351 | 1421 |
| Mystery Game Puzzles | 5% | 17% |
| DTBench | 77.6% | 84.3% |
| LMCA | 26.5% | 32.2% |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 51.7% |
| ARC-AGI-1 | 58.7% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| Thematic Generalization | — | 51.2% |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |

## Math

- o4-mini: 40.8 (#89)
- Qwen3.5 122B-A10B: 39.1 (#112)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1389 | 1432 |
| 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)
- Qwen3.5 122B-A10B: 38.8 (#142)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 18.6% | 11.2% |
| LMArena Expert | 1343 | 1432 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| GPQA (HELM) | 73.5% | — |

## Multimodal

- o4-mini: 40.2 (#49)
- Qwen3.5 122B-A10B: 39.6 (#57)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1194 | 1245 |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |

## Multilingual

- o4-mini: 47.0 (#154)
- Qwen3.5 122B-A10B: 51.6 (#107)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1337 | 1400 |
| LMArena Chinese | 1354 | 1462 |
| LMArena French | 1364 | 1442 |
| LMArena German | 1336 | 1426 |
| LMArena Japanese | 1308 | 1367 |
| LMArena Korean | 1312 | 1352 |
| LMArena Russian | 1334 | 1400 |
| LMArena Spanish | 1347 | 1424 |

## Instruction Following

- o4-mini: 75.2 (#68)
- Qwen3.5 122B-A10B: 73.8 (#115)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1399 |
| IFEval | 92.8% | — |

## Long Context

- o4-mini: 45.5 (#33)
- Qwen3.5 122B-A10B: 43.0 (#109)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1315 | 1410 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- o4-mini: 54.0 (#152)
- Qwen3.5 122B-A10B: 60.0 (#105)

| Benchmark | o4-mini | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1353 | 1417 |
| LMArena Creative Writing | 1294 | 1368 |
| LMArena Multi-Turn | 1350 | 1416 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |

## FAQ

### Is o4-mini better than Qwen3.5 122B-A10B?

o4-mini and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.6 vs 42.1), so choose on price, context window or the category you care about most.

### Which is cheaper, o4-mini or Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; o4-mini lists at $1.10 and $4.40.

### Is o4-mini or Qwen3.5 122B-A10B better for coding?

o4-mini scores higher on coding benchmarks: 40.9 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5 122B-A10B does, with 262K tokens against 200K.

### How many benchmarks do o4-mini and Qwen3.5 122B-A10B share?

23 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen3.5 122B-A10B has 27.