Model evidence
Good enough for which task?
Explore measured models and available catalog listings. Quality comes from published task evidence; models without task results are clearly marked.
| Model | Evidence | Cheapest passing | Median quality | Providers |
|---|---|---|---|---|
Model evidence
Explore measured models and available catalog listings. Quality comes from published task evidence; models without task results are clearly marked.
| Model | Evidence | Cheapest passing | Median quality | Providers |
|---|---|---|---|---|
| Model | Evidence | Cheapest passing | Median quality | Providers |
|---|---|---|---|---|
| typesafe-ai/jev Unclassified | Not yet measured | — | — | TrustedRouter |
| unbiased/pareto Unclassified | Not yet measured | — | — | OpenRouter |
| unbiased/pareto-26.10-preview Unclassified | Not yet measured | — | — | OpenRouter |
| undi95/remm-slerp-l2-13b Unclassified | Not yet measured | — | — | OpenRouterTrustedRouter |
| upstage/solar-mini4 Unclassified | Not yet measured | — | — | OpenRouter |
| upstage/solar-pro-3 Unclassified | Not yet measured | — | — | OpenRouter |
| upstage/solar-pro2 Unclassified | Not yet measured | — | — | TrustedRouter |
| upstage/solar-pro3 Unclassified | Not yet measured | — | — | TrustedRouter |
| upstage/solar-pro4 Unclassified | Not yet measured | — | — | OpenRouterTrustedRouter |
| us.anthropic.claude-opus-4-6-v1 Unclassified | Not yet measured | — | — | Price unavailable |
| us.anthropic.claude-opus-4-7 Unclassified | Not yet measured | — | — | Price unavailable |
| us.anthropic.claude-sonnet-4-6 Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/affedevit-eval-dataset-593a6dec Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/benchmark-inbox-triage-granite-4-1-8b-e301a753-retry-8fd8f67a Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/chess-assistant-39f09ea2 Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/chess-assistant-c91ec5a9 Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/gemma-4-12b-it-w8a8 Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/google/diffusiongemma-26B-A4B-it Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/google/gemma-4-E2B-it Unclassified | Not yet measured | — | — | Price unavailable |
| vllm/lowes-toolcall-v6 Unclassified | Not yet measured | — | — | Price unavailable |
Cheapest passing counts tasks where the model clears the task’s published quality floor (80% when none is recorded) and has the lowest observed workload cost. Median quality summarizes those published task results; it is not a general model ranking.