Qwen3.5 397B-A17B
Qwen3.5 397B-A17B (Alibaba) was released on Feb 13, 2026. In the Epoch AI capability ranking (ECI), it ranks #76 out of 267 models, with 146.66. On Arena, which measures human preference in blind comparisons, it has 1,499 ELO points (#55). Against models of the same generation, its best result is on Dtbench: 87.5%, #18 of 57.
Where Qwen3.5 397B-A17B stands out and where it falls behind, by the numbers
Qwen3.5 397B-A17B has published results on 7 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between May 19, 2025 and May 14, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 7 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 86.4% | #24 / 61 | #61 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 88.9% | #21 / 61 (tied with 2) | #59 / 168 | 100.0% GPT-5.5 |
| Dtbench | 87.5% | #18 / 57 | #50 / 148 | 98.9% Claude Opus 5.5 |
| Lmca | 37.89 | #21 / 54 | #53 / 121 | 68.23 Claude Opus 5.5 |
| Frontiermath Tiers 1 3 V2 | 31.2% | #24 / 34 | #66 / 86 | 93.7% GPT-6 Astra |
| Game puzzles | 18.0% | #15 / 30 (tied with 1) | #48 / 77 | 84.0% GPT-6 Astra |
| Apex Agents | 24.9% | #8 / 10 | #47 / 50 | 82.4% Gemini 4 Argon |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare Qwen3.5 397B-A17B with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| MiniMax-M3 | MiniMax | 147.13 | 1,471 | 67.3 | Jun 1, 2026 |
| Mistral Large 4 | Mistral AI | 146.90 | 1,494 | 71.8 | Oct 6, 2026 |
| Claude Sonnet 4.5 | Anthropic | 146.83 | 1,488 | n/a | Sep 29, 2025 |
| MiniMax-M2.5 | MiniMax | 146.67 | 1,393 | n/a | Feb 12, 2026 |
| Qwen3.5 397B-A17B | Alibaba | 146.66 | 1,499 | n/a | Feb 13, 2026 |
| Grok 4 | xAI | 146.43 | n/a | n/a | Jul 9, 2025 |
| DeepSeek v4 (unknown) | DeepSeek | 146.26 | n/a | n/a | Apr 24, 2026 |
Qwen3.5 397B-A17B or Claude Sonnet 4.5?
Claude Sonnet 4.5 is the model from another lab closest to Qwen3.5 397B-A17B in capability. Across the 6 tests both took, this is the score:
| Test | Qwen3.5 397B-A17B | Claude Sonnet 4.5 |
|---|---|---|
| Frontiermath Tiers 1 3 V2 | 31.2% | 23.9% |
| AIME 2024 and 2025 (OTIS) | 88.9% | 77.8% |
| Game puzzles | 18.0% | 17.0% |
| Dtbench | 87.5% | 83.2% |
| GPQA Diamond | 86.4% | 82.3% |
| Lmca | 37.89 | 38.76 |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Alibaba
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Qwen 3.6 Max (Preview) | Apr 20, 2026 | 149.24 | 1,488 | n/a | Unknown |
| Qwen 3.6 35B-A3B | Apr 14, 2026 | 144.11 | n/a | n/a | Open weights (unrestricted) |
| Qwen 3.6 Plus | Mar 31, 2026 | 147.49 | 1,476 | 68.9 | API access |
| Qwen 3.5 Flash (hosted 35B-A3B) | Feb 25, 2026 | 143.77 | 1,446 | n/a | Unknown |
| Qwen3.5-122B-A10B | Feb 24, 2026 | 146.26 | 1,466 | n/a | Open weights (restricted use) |
| Qwen3.5-35B-A3B | Feb 24, 2026 | 142.48 | 1,457 | n/a | Open weights (unrestricted) |
| Qwen3.5-9B | Feb 24, 2026 | 139.43 | n/a | n/a | Open weights (restricted use) |
| Qwen 3.5 Plus (hosted 397B-A17B) | Feb 16, 2026 | 146.32 | n/a | n/a | Unknown |
| Qwen3.5 397B-A17B | Feb 13, 2026 | 146.66 | 1,499 | n/a | Open weights (unrestricted) |
Have you used Qwen3.5 397B-A17B? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about Qwen3.5 397B-A17B
Where does Qwen3.5 397B-A17B rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Qwen3.5 397B-A17B ranks #76 out of 267 models, with an ECI of 146.66. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is Qwen3.5 397B-A17B better than Claude Sonnet 4.5?
Across the 6 tests both models took and Epoch AI compiled, Qwen3.5 397B-A17B comes out ahead on 5, behind on 1 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
What is Qwen3.5 397B-A17B best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of Qwen3.5 397B-A17B are: Dtbench (#18 of 57). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking