Qwen3-30B-A3B: benchmark scores, price and ranking
Qwen3-30B-A3B from Alibaba ranks #612 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.9), based on 8 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-04-28 (source: epoch)
- Cheapest API price
- $0.090 in / $0.200 out per million tokens (via pinstripes, observed 2026-10-13T19:47Z)
- Aggregate rank
- #612 of 743 (score 44.9)
Relative to other models, Qwen3-30B-A3B is strongest on Epoch ECI (#66 of 204) and weakest on Fiction.liveBench (#42 of 47).
Across the 8 benchmarks where at least ten models are scored, Qwen3-30B-A3B is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.090 per million tokens, is lower than that of 83% of the 427 models with a listed price.
Qwen3-30B-A3B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 136 | #66 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 62.8% | #90 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 61.7% | #165 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 4.0% | #85 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 60.3% | #102 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 15.8% | #85 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 29.8% | #87 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 40.6% | #42 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Qwen3-30B-A3B
Qwen3-30B-A3B is an open-weight model that can run on your own hardware from Alibaba. It was released on 2025-04-28, according to Epoch AI. The cheapest API listing we track charges $0.090 per million input tokens and $0.200 per million output tokens, through pinstripes. We hold 8 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where Qwen3-30B-A3B stands
On our aggregate score, Qwen3-30B-A3B is #612 of 743 ranked models, in the lower half. Its score is 44.9; the scale is centred on 50, so it sits 5.1 points below the typical model. That beats 18% of the ranked field. Among the 74 ranked Alibaba models it is #66. The next one up is qwen2.5-32b-instruct at 45.0. The next one down is Qwen3.6 27B at 44.9.
Qwen3-30B-A3B, benchmark by benchmark
Epoch ECI puts Qwen3-30B-A3B at 136, #66 of 204. That beats 68% of the models tested, but 20 points short of Qwen 3.8 Max (156). The results either side are GPT-4.5 (137) and qwen3-8b (136). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen3-30B-A3B is 9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On OTIS Mock AIME, Qwen3-30B-A3B reaches 62.8%. It ranks #90 of 189, ahead of 52% of the field, and 37.2 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are claude-opus-4-1-20250805_16K (64.4%) and qwen3-30b-a3b-instruct-2507 (62.2%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3-30B-A3B is 5.0 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3-30B-A3B lands below the middle on GPQA Diamond: 61.7%, #165 of 275, with 60% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is qwen3-4b-instruct-2507 at 62.0%. It covers expert-level science questions. The board median is 71.7%, so Qwen3-30B-A3B is 10.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3-30B-A3B lands below the middle on Chess Puzzles: 4.0%, #85 of 122, with 69% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is qwen3-14b at 4.0%. It covers chess tactics puzzles. The board median is 12.5%, so Qwen3-30B-A3B is 8.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3-30B-A3B lands below the middle on DTBench: 60.3%, #102 of 146, with 69% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is mistral-large-2411 at 60.8%. It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen3-30B-A3B is 8.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3-30B-A3B lands below the middle on LMCA: 15.8%, #85 of 108, with 78% of the field scoring higher. Claude Opus 5.5 (max) leads at 68.2%; the closest result above is Llama 4 Maverick at 15.9%. It covers language-model capability assessment. The board median is 29.2%, so Qwen3-30B-A3B is 13.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Qwen3-30B-A3B lands below the middle on WeirdML: 29.8%, #87 of 109, with 79% of the field scoring higher. GPT-6 Astra (max) leads at 93.3%; the closest result above is Claude 3.5 Haiku (Oct 2024) at 30.7%. It covers unusual machine-learning tasks. The board median is 41.2%, so Qwen3-30B-A3B is 11.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Fiction.liveBench is a weak spot. Qwen3-30B-A3B scores 40.6%, #42 of 47, behind 87% of the models measured. The leader, grok-4-0709, reaches 94.4%. It covers long-context story comprehension (16k). The board median is 61.1%, so Qwen3-30B-A3B is 20.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 46% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#90 of 189) and its weakest is GPQA Diamond (#165 of 275). General knowledge and chat: uneven, ahead of 30% of the field on average across 5 benchmarks. Its best board here is Epoch ECI (#66 of 204) and its weakest is Fiction.liveBench (#42 of 47).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3-30B-A3B costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on ollama/mistral-small ($0.100) and Llama-2-13b-chat ($0.100).
Release history
The Alibaba model released before it was qwen3-14b on 2025-04-28, which scores 45.6. The next one was qwen3-8b on 2025-04-28, at 43.4.
Reading these numbers
The 8 scores on this page come from 1 source: Epoch AI Benchmarking Hub (8). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 1 other reasoning-effort setting of this model, which redirect here. This page shows the highest.
Qwen3-30B-A3B is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #609 mistral-small-3-2501 (45.0)
- #610 GLM-4.6 (45.0)
- #611 qwen2.5-32b-instruct (45.0)
- #613 aya-expanse-8b (44.9)
- #614 Mercury 2 (44.9)
- #615 Qwen3.6 27B (44.9)
More from Alibaba
- Qwen 3.6 Max (Preview) (#25, 54.1)
- Qwen3.8 Max (xhigh) (#37, 53.2)
- Qwen3.7 Max (#71, 52.3)
- ollama/qwen2.5-coder:32b (#93, 51.9)
- Qwen3 235B A22B diff, no think, Alibaba API (#122, 51.5)
- Qwen2.5-Coder-14B-Instruct (#135, 51.3)
Compare it on the live leaderboard → · How the aggregate score works