Qwen3.5-122B-A10B: benchmark scores, price and ranking
Qwen3.5-122B-A10B from Qwen ranks #46 of 743 LLMs on the LLMs Tiger aggregate benchmark score (53.0), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Qwen
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-02-24 (source: epoch)
- Cheapest API price
- $0.113 in / $0.901 out per million tokens (via aihubmix, observed 2026-10-13T20:47Z)
- Aggregate rank
- #46 of 743 (score 53.0)
Across the 2 benchmarks where at least ten models are scored, Qwen3.5-122B-A10B is in the top 10% on 1 and in the top half on 2.
Its cheapest listed input price, $0.113 per million tokens, is lower than that of 78% of the 427 models with a listed price.
Qwen3.5-122B-A10B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 86.7% | #8 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
| GPQA Diamond | 86.6% | #64 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About Qwen3.5-122B-A10B
Qwen3.5-122B-A10B is an open-weight model that can run on your own hardware from Qwen. It was released on 2026-02-24, according to Epoch AI. The cheapest API listing we track charges $0.113 per million input tokens and $0.901 per million output tokens, through aihubmix. We hold 2 benchmark results for it across 1 area, and 1 is in the top tenth of its board.
Where Qwen3.5-122B-A10B stands
On our aggregate score, Qwen3.5-122B-A10B is #46 of 743 ranked models, in the top fifty. Its score is 53.0; the scale is centred on 50, so it sits 3.0 points above the typical model. That beats 94% of the ranked field. Among the 23 ranked Qwen models it is #1. The next one down is Qwen3-Coder-30B-A3B-Instruct at 52.7.
Qwen3.5-122B-A10B, benchmark by benchmark
On MMLU-Pro, Qwen3.5-122B-A10B scores 86.7% and ranks #8 of 136. Only 7 models score higher, led by Darwin-180B-RSI at 88.1%, which is 1.4 points ahead. It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Qwen3.5-122B-A10B is 31.4 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
On GPQA Diamond, Qwen3.5-122B-A10B reaches 86.6%. It ranks #64 of 275, ahead of 77% of the field, and 9.2 points behind GPT-6 Astra (max) at 95.8%. The results either side are GPT-5.4 mini (xhigh) (86.9%) and Ornith-1.5-9B (86.4%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.5-122B-A10B is 14.9 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: strong, ahead of 85% of the field on average across 2 benchmarks. Its best board here is MMLU-Pro (#8 of 136) and its weakest is GPQA Diamond (#64 of 275).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.5-122B-A10B costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), GLM-5.2 (high) ($0.060, 51.6), Qwen3-Coder-30B-A3B-Instruct ($0.070, 52.7). Similar scores cost more on MiMo-V2.6 Flash ($0.140) and DeepSeek-V3.2-Exp (high) ($0.270).
Release history
The Qwen model released before it was qwen3-4b-instruct-2507 on 2025-08-06, which scores 48.7. The next one was Qwen3.8-2.4T-A95B on 2026-08-12, at 52.1.
Reading these numbers
The 2 scores on this page come from 2 sources: HuggingFace GPQA Diamond leaderboard (1), HuggingFace MMLU-Pro leaderboard (1). 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. With 2 results the aggregate rank can move a lot when one new score arrives.
Qwen3.5-122B-A10B 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
- #43 o3 + gpt-4.1 (53.1)
- #44 NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (53.1)
- #45 Claude Code + Sonnet 5.5 (53.0)
- #47 Claude Mythos Preview (Early) (53.0)
- #48 Gemini 2.5 Pro Preview 05-06 (53.0)
- #49 Solar-Open2-250B (52.9)
More from Qwen
- Qwen3-Coder-30B-A3B-Instruct (#53, 52.7)
- Qwen3.8-2.4T-A95B (#79, 52.1)
- Qwen3.8-Flash-Next (#96, 51.8)
- Qwen3-4B-Thinking-2507 (#276, 49.3)
- TTS(Bo8) (#295, 49.1)
- Qwen2.5-14B (#302, 49.0)
Compare it on the live leaderboard → · How the aggregate score works