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 |
|---|---|---|---|---|
| recraft/recraftv2 Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv3 Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4 Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4_1 Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4_1_pro Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4_1_utility Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4_1_utility_pro Unclassified | Not yet measured | — | — | TrustedRouter |
| recraft/recraftv4_pro Unclassified | Not yet measured | — | — | TrustedRouter |
| reka/reka-edge-2603 Unclassified | Not yet measured | — | — | TrustedRouter |
| rekaai/reka-edge Unclassified | Not yet measured | — | — | OpenRouter |
| rekaai/reka-flash-3 Unclassified | Not yet measured | — | — | OpenRouter |
| relace/relace-apply-3 Unclassified | Not yet measured | — | — | OpenRouter |
| relace/relace-search Unclassified | Not yet measured | — | — | OpenRouter |
| runway/gen-4.5 Unclassified | Not yet measured | — | — | TrustedRouter |
| sakana-ai/fugu-ultra-v1.1 Unclassified | Not yet measured | — | — | TrustedRouter |
| sakana-ai/sakana-namazu-v1.0 Unclassified | Not yet measured | — | — | TrustedRouter |
| sakana/fugu-max Unclassified | Not yet measured | — | — | OpenRouter |
| sakana/fugu-ultra Unclassified | Not yet measured | — | — | OpenRouter |
| sakana/fugu-ultra-v2 Unclassified | Not yet measured | — | — | OpenRouter |
| sakana/sakana-namazu Unclassified | Not yet measured | — | — | OpenRouter |
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.