| model | trendline | today | 7d | 30d | flags (today) | latency ms p50 / p95 |
|---|---|---|---|---|---|---|
| anthropic | ||||||
| claude-sonnet-5 | 94% | 96% (7d) | 97% (26d) | low today: instruction 67% | 1475 / 13139 | |
| claude-haiku-4-5 | 86% | 86% (7d) | 86% (26d) | low today: tool-call 50% | 858 / 5825 | |
| openai | ||||||
| gpt-5 | 97% | 95% (7d) | 93% (26d) | nothing to flag | 1190 / 15914 | |
| gpt-5-mini | 91% | 93% (7d) | 92% (26d) | low today: capability 73% | 1425 / 18563 | |
| gpt-5.6-terra | 93% | 94% (7d) | 92% (26d) | low today: instruction 60% | 1378 / 23523 | |
| gpt-5.6-luna | 95% | 95% (7d) | 94% (26d) | nothing to flag | 1045 / 8700 | |
| gemini-3.1-pro-preview | 100% | 100% (7d) | 100% (25d) | watch: latency p50 4232→7406 ms (context, not logged) | 7406 / 23394 | |
| gemini-3.5-flash | 100% | 100% (7d) | 100% (26d) | nothing to flag | 947 / 5337 | |
| deepseek | ||||||
| deepseek-chat@deepseek | 100% | 96% (7d) | 87% (26d) | nothing to flag | 1128 / 4060 | |
| deepseek-reasoner@deepseek | 99% | 99% (7d) | 98% (23d) | movement: thinking tokens refusal 502→1674 watch: thinking tokens structured 27→43 movement: thinking tokens sycophancy 106→1326 movement: thinking tokens verbosity 180→1059 3 errored calls | 1328 / 23412 | |
| mistral | ||||||
| mistral-large@mistral | 92% | 92% (7d) | 92% (26d) | low today: instruction 60% | 970 / 12754 | |
| mistral-small@mistral | 86% | 86% (7d) | 86% (26d) | low today: capability 60% low today: instruction 60% | 642 / 6304 | |
| sarvam | ||||||
| sarvam-105b@sarvam | 92% | 91% (7d) | 89% (26d) | low today: instruction 73% | 1118 / 15781 | |
| moonshot | ||||||
| kimi-k3@moonshot | 100% | 100% (7d) | 100% (19d) | nothing to flag | 7518 / 81075 | |
| xai | ||||||
| grok-4.6@xai | 100% | 100% (7d) | 100% (23d) | nothing to flag | 5720 / 27404 | |
| deepinfra | ||||||
| qwen3-235b@deepinfra | 95% | 94% (7d) | 94% (17d) | low today: instruction 73% | 2306 / 57213 | |
| glm-5.2@deepinfra | 100% | 100% (7d) | 100% (17d) | 2 errored calls | 6374 / 50838 | |
| llama-4-maverick@deepinfra | 100% | 100% (7d) | 100% (17d) | nothing to flag | 706 / 10920 | |
| minimax-m2.5@deepinfra | 100% | 99% (7d) | 96% (17d) | watch: latency p50 4992→8006 ms (context, not logged) | 8006 / 53169 | |
| model | trendline | today | 7d | 30d | status | latency ms p50 / p95 |
|---|---|---|---|---|---|---|
| anthropic | ||||||
| claude-sonnet-5 | 99% | 99% (4d) | 99% (4d) | baseline accruing (4 of 7 deep readings) | 1174 / 8200 | |
| claude-haiku-4-5 | 95% | 96% (4d) | 96% (4d) | baseline accruing (4 of 7 deep readings) | 589 / 3986 | |
| claude-opus-5 | 99% | 99% (4d) | 99% (4d) | baseline accruing (4 of 7 deep readings) | 1661 / 26956 | |
| claude-fable-5 | 97% | 98% (4d) | 98% (4d) | baseline accruing (4 of 7 deep readings) | 3375 / 11117 | |
| claude-fable-5.1 | 99% | 99% (2d) | 99% (2d) | baseline accruing (2 of 7 deep readings) | 3116 / 14878 | |
| openai | ||||||
| gpt-5 | 98% | 96% (4d) | 96% (4d) | baseline accruing (4 of 7 deep readings) | 717 / 6026 | |
| gpt-5-mini | 96% | 92% (4d) | 92% (4d) | baseline accruing (4 of 7 deep readings) | 696 / 6655 | |
| gpt-5.6-terra | 98% | 97% (4d) | 97% (4d) | baseline accruing (4 of 7 deep readings) | 787 / 6626 | |
| gpt-5.6-luna | 95% | 93% (4d) | 93% (4d) | baseline accruing (4 of 7 deep readings) | 806 / 3393 | |
| gpt-5.6-sol | 98% | 96% (4d) | 96% (4d) | baseline accruing (4 of 7 deep readings) | 953 / 5914 | |
| gpt-6-astra | 96% | 97% (2d) | 97% (2d) | baseline accruing (2 of 7 deep readings) | 1334 / 7708 | |
| gemini-3.1-pro-preview | 100% | 99% (3d) | 99% (3d) | baseline accruing (3 of 7 deep readings) | 2933 / 6764 | |
| gemini-3.5-flash | 100% | 100% (4d) | 100% (4d) | baseline accruing (4 of 7 deep readings) | 752 / 2677 | |
| deepseek | ||||||
| deepseek-chat@deepseek | 99% | 96% (4d) | 96% (4d) | baseline accruing (4 of 7 deep readings) | 1063 / 3072 | |
| deepseek-reasoner@deepseek | 98% | 96% (4d) | 96% (4d) | baseline accruing (4 of 7 deep readings) | 1284 / 11407 | |
| mistral | ||||||
| mistral-large@mistral | 85% | 85% (4d) | 85% (4d) | baseline accruing (4 of 7 deep readings) | 652 / 6398 | |
| mistral-small@mistral | 98% | 98% (4d) | 98% (4d) | baseline accruing (4 of 7 deep readings) | 440 / 2944 | |
| sarvam | ||||||
| sarvam-105b@sarvam | 99% | 95% (4d) | 95% (4d) | baseline accruing (4 of 7 deep readings) | 864 / 5192 | |
| moonshot | ||||||
| kimi-k3@moonshot | 95% | 97% (4d) | 97% (4d) | baseline accruing (4 of 7 deep readings) | 7126 / 57498 | |
| xai | ||||||
| grok-4.6@xai | 98% | 98% (4d) | 98% (4d) | baseline accruing (4 of 7 deep readings) | 4223 / 21528 | |
| deepinfra | ||||||
| qwen3-235b@deepinfra | 100% | 100% (3d) | 100% (3d) | baseline accruing (3 of 7 deep readings) | 913 / 27500 | |
| glm-5.2@deepinfra | 99% | 99% (3d) | 99% (3d) | baseline accruing (3 of 7 deep readings) | 3824 / 32647 | |
| llama-4-maverick@deepinfra | 98% | 96% (3d) | 96% (3d) | baseline accruing (3 of 7 deep readings) | 399 / 7586 | |
| minimax-m2.5@deepinfra | 95% | 95% (3d) | 95% (3d) | baseline accruing (3 of 7 deep readings) | 7112 / 73786 | |