Model comparison
o3-mini vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 36.7 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. o3-mini scores higher in 3 categories and Qwen3-30B-A3B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-30B-A3B leads 37.4 to 28.1.
- The biggest single-benchmark swing is WeirdML: 43.7% for o3-mini and 29.8% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- o3-mini accepts more context: 200K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Qwen3-30B-A3B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 38.9 |
| Released | 2024-12-20 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 200K | 41K |
| Max output | 100K | 16K |
| Input $ / M tokens | $1.10 | $0.12 |
| Output $ / M tokens | $4.40 | $0.50 |
| Results tracked | 51 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 39.8% | 33.3% |
| WeirdML | 43.7% | 29.8% |
| LMArena Coding | 1378 | 1416 |
| Aider Polyglot | 60.4% | — |
| GSO | 1.3% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Too close to call
o3-mini: 29.6 (#84), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Cybench | 22.5% | — |
Reasoning Qwen3-30B-A3B leads
o3-mini: 16.3 (#305), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 0.3% | 0.3% |
| Chess Puzzles | 17% | 8% |
| LMArena Hard Prompts | 1366 | 1398 |
| DTBench | 68.8% | 69.3% |
| LMCA | 19% | 22.4% |
| Epoch Capabilities Index | 140.34 | 139.63 |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| Kagi LLM Benchmark | — | 54.9% |
| ARC-AGI-1 | 34.5% | — |
| LiveBench Reasoning | 89.6% | — |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | 70.6% | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Qwen3-30B-A3B leads
o3-mini: 28.1 (#244), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 76.9% | 70.3% |
| LMArena Math | 1396 | 1394 |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| MathArena Final-Answer Competitions | — | 47.8% |
| LiveBench Math | 77.3% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3-30B-A3B leads
o3-mini: 38.3 (#146), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 77% | 70.1% |
| Confabulations | 17.9% | 12.3% |
| LMArena Expert | 1364 | 1396 |
| SimpleQA Verified | 15.3% | — |
Multilingual Qwen3-30B-A3B leads
o3-mini: 45.7 (#164), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1319 | 1372 |
| LMArena Chinese | 1379 | 1433 |
| LMArena French | 1334 | 1418 |
| LMArena German | 1303 | 1380 |
| LMArena Japanese | 1286 | 1337 |
| LMArena Korean | 1314 | 1331 |
| LMArena Russian | 1304 | 1370 |
| LMArena Spanish | 1321 | 1404 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1337 | 1363 |
| LiveBench Instruction Following | 84.4% | — |
Long Context o3-mini leads
o3-mini: 33.8 (#256), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | 50% | 40.6% |
| LMArena Longer Query | 1343 | 1379 |
Writing & Preference Qwen3-30B-A3B leads
o3-mini: 50.3 (#182), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | o3-mini | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1337 | 1384 |
| LMArena Creative Writing | 1286 | 1317 |
| Short-Story Creative Writing | 61.7% | 75.3% |
| LMArena Multi-Turn | 1320 | 1378 |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini 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; o3-mini lists at $1.10 and $4.40.
Is o3-mini or Qwen3-30B-A3B better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 41K.
How many benchmarks do o3-mini and Qwen3-30B-A3B share?
29 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen3-30B-A3B has 32.