# o1 vs Qwen3-30B-A3B

> o1 is the stronger model overall, scoring 40.6 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 122× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/o1-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. o1 scores higher in 4 categories and Qwen3-30B-A3B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 31.0.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for o1 and 40.6% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $15 / $60 for o1.
- o1 accepts more context: 200K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.

## Snapshot

| | o1 | Qwen3-30B-A3B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 40.6 | 38.5 |
| Rank | 140 | 174 |
| Context | 200K | 41K |
| Input $/M | $15 | $0.12 |
| Output $/M | $60 | $0.50 |
| Weights | Proprietary | Open |

## Coding

- o1: 45.7 (#64)
- Qwen3-30B-A3B: 37.0 (#188)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| WeirdML | 47.6% | 29.8% |
| LMArena Coding | 1367 | 1416 |
| Aider Polyglot | 61.7% | — |
| SciCode | — | 33.3% |
| LiveBench Coding | 69.7% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |

## Agentic & Tool Use

- o1: 24.3 (#111)
- Qwen3-30B-A3B: 29.5 (#75)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |

## Reasoning

- o1: 27.5 (#103)
- Qwen3-30B-A3B: 21.6 (#193)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| Chess Puzzles | 15% | 8% |
| LMArena Hard Prompts | 1372 | 1398 |
| DTBench | 74.7% | 69.3% |
| LMCA | 22.3% | 22.4% |
| Epoch Capabilities Index | 141.92 | 139.63 |
| SimpleBench | 41.7% | — |
| Kagi LLM Benchmark | — | 54.9% |
| ARC-AGI-1 | 30.7% | — |
| CritPt | — | 0.3% |
| EnigmaEval | 5.7% | — |
| LiveBench Reasoning | 91.6% | — |
| LiveBench Data Analysis | 65.5% | — |
| LiveBench | 75.7% | — |

## Math

- o1: 34.9 (#150)
- Qwen3-30B-A3B: 36.0 (#133)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 70.3% |
| LMArena Math | 1388 | 1394 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| MathArena Final-Answer Competitions | — | 47.8% |
| LiveBench Math | 80.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |

## Knowledge

- o1: 41.5 (#101)
- Qwen3-30B-A3B: 41.7 (#96)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 76.8% | 70.1% |
| Confabulations | 11.7% | 12.3% |
| LMArena Expert | 1362 | 1395 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |

## Multimodal

- o1: 33.6 (#87)
- Qwen3-30B-A3B: —

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |

## Multilingual

- o1: 48.8 (#137)
- Qwen3-30B-A3B: 49.8 (#126)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1359 | 1372 |
| LMArena Chinese | 1394 | 1434 |
| LMArena French | 1343 | 1419 |
| LMArena German | 1337 | 1379 |
| LMArena Japanese | 1346 | 1338 |
| LMArena Korean | 1396 | 1333 |
| LMArena Russian | 1356 | 1369 |
| LMArena Spanish | 1345 | 1403 |

## Instruction Following

- o1: 75.0 (#82)
- Qwen3-30B-A3B: 72.2 (#137)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1368 | 1364 |
| LiveBench Instruction Following | 81.5% | — |

## Long Context

- o1: 50.3 (#9)
- Qwen3-30B-A3B: 31.0 (#278)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | 83.3% | 40.6% |
| LMArena Longer Query | 1378 | 1379 |

## Writing & Preference

- o1: 55.8 (#139)
- Qwen3-30B-A3B: 55.9 (#138)

| Benchmark | o1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1366 | 1384 |
| LMArena Creative Writing | 1347 | 1318 |
| Short-Story Creative Writing | 70.2% | 75.3% |
| LMArena Multi-Turn | 1368 | 1378 |
| LiveBench Language | 65.4% | — |

## FAQ

### Is o1 better than Qwen3-30B-A3B?

o1 is the stronger model overall, scoring 40.6 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 122× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

### Which is cheaper, o1 or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; o1 lists at $15 and $60.

### Is o1 or Qwen3-30B-A3B better for coding?

o1 scores higher on coding benchmarks: 45.7 versus 37.0 in the Noometry coding category.

### Which has the bigger context window?

o1 does, with 200K tokens against 41K.

### How many benchmarks do o1 and Qwen3-30B-A3B share?

27 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Qwen3-30B-A3B has 32.