Qwen3 235B A22B Thinking 2507
Timed at 20 tok/s, scored 22.1 on the Coding Index, on 6 Design Arena boards, and with results on 1 openly licensed board.
retrieved sha256 · 0bb53a77713f
Measured speed
70 requests · 1 endpoint · 30-minute windowOpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.
Every endpoint
1 priced · 1 timed · cheapest first- Venicevenice/fp8 · listed$0.45$3.50not listedfp816k20 tok/s141.04s70 req100%
Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . The one seller with a reading, Venice at 96.60% on 2 Nov 2026, fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.
Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .
What each seller accepts
11 parameters · 1 seller- frequency_penaltyevery seller
- include_reasoningevery seller
- max_tokensevery seller
- presence_penaltyevery seller
- reasoningevery seller
- stopevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_kevery seller
- top_pevery seller
The one seller that publishes a list accepts these 11. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $1.213 per million tokens, 3 in to 1 out: cheaper than 131 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.
Measured quality
145 models with an index · 132 on a design arena boardEach mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.
- 3D scenes · Models977 Elowin rate 40.4% · source rank 122the board, 113 ranked
- Code · Models1021 Elowin rate 40.8% · source rank 127the board, 120 ranked
- Data visualisation · Models950 Elowin rate 32.6% · source rank 124the board, 110 ranked
- Game development · Models946 Elowin rate 34.2% · source rank 136the board, 120 ranked
- UI components · Models933 Elowin rate 34.0% · source rank 132the board, 116 ranked
- Websites · Models1043 Elowin rate 42.0% · source rank 127the board, 126 ranked
Position 109 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.
Benchmark results
1 of 6 boards · 4 results| Task | All runs | Score |
|---|---|---|
| GPQA diamond | 342 | 0.80 |
| Mystery Game Puzzles | 149 | 0.09 |
| OTIS Mock AIME 2024-2025 | 319 | 0.87 |
| SimpleQA Verified | 106 | 0.40 |
Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names this run Qwen3-235B-A22B-Thinking-2507, with no effort setting written on it. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
1 of the 6 openly licensed boards Vitna mirrors carries a result for Qwen3 235B A22B Thinking 2507, each printed as its publisher published it and none added to another. MTEB, LiveBench, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.
Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.
