Models
Three ways a model can differ from the rest of the field. None of them is a score of quality — a model that hedges, or that answers differently from everyone else, is a data point, not a mistake. A dash means too few questions to report.
- Consistency — how often it gives the same answer when asked again. How it's measured →
- Alignment — how often its answer is the one most other models gave. How it's measured →
- Hedging — how often it qualifies its answer or declines to give one. How it's measured →
139 models
Consistency Alignment Hedging
inception/mercury-decide:free Inception · 2026-09-30 83.581.10 openai/gpt-6.1-sol OpenAI · 2026-09-29 81.176.630.1 anthropic/claude-sonnet-5.5 Anthropic · 2026-09-28 75.273.218.4 upstage/solar-decide Upstage · 2026-09-28 81.251.40 jaredpalmer/kev-4b Jared Palmer · 2026-09-25 78.589.20 upstage/solar-mini4 Upstage · 2026-09-23 62.370.242.1 anthropic/claude-opus-5.5 Anthropic · 2026-09-22 80.586.734.2 openai/gpt-6-luna OpenAI · 2026-09-22 75.37530 openai/gpt-6-sol OpenAI · 2026-09-22 73.584.326.7 qwen/qwen3.8-omni-flash Qwen · 2026-09-21 ——— x-ai/grok-4.7 xAI · 2026-09-21 68.68121.5 xiaomi/mimo-v2.6-flash Xiaomi · 2026-09-21 ——— xiaomi/mimo-v2.6-pro Xiaomi · 2026-09-21 ——— typesafe/jev-1.13 TypeSafe · 2026-09-18 89.964.90 sakana/fugu-max Sakana · 2026-09-11 ——— deepseek/deepseek-v4.1-flash DeepSeek · 2026-09-10 ——— inception/mercury-2.5 Inception · 2026-09-08 74.68133.4 openai/gpt-6-astra OpenAI · 2026-09-04 —71.416.1 qwen/qwen3.8-max-0902 Qwen · 2026-09-03 —77.36.3 google/gemini-3.8-flash Google · 2026-09-02 —8115.3 meta/muse-spark-1.3 Meta · 2026-09-02 —81.83 anthropic/claude-fable-5.1 Anthropic · 2026-09-01 —8020.8 ibm-granite/granite-4.2-8b IBM · 2026-08-31 ——— tencent/hy4-preview Tencent · 2026-08-28 —77.311.7 qwen/qwen3.8-flash Qwen · 2026-08-26 —8513.7 z-ai/glm-5.3-flash Z.ai · 2026-08-26 —90.517.4 tencent/hy-mt2-30b-a3b Tencent · 2026-08-20 —61.96.9 z-ai/glm-5.3 Z.ai · 2026-08-18 —71.414.3 qwen/qwen3.8-27b Qwen · 2026-08-14 —8115 google/gemini-3.7-flash Google · 2026-08-13 ——23.9 bytedance-seed/seed-2-1-turbo Bytedance · 2026-08-12 —8024.4 deepseek/deepseek-v4-pro-0813 DeepSeek · 2026-08-12 —63.66.9 x-ai/grok-4.6 xAI · 2026-08-12 —63.63.5 nvidia/nemotron-3.5-lightning NVIDIA · 2026-08-11 —71.415.4 upstage/solar-pro4 Upstage · 2026-08-10 57.669.233.2 meta/muse-glimmer-30b Meta · 2026-08-09 ——25.3 meta/muse-spark-1.2 Meta · 2026-08-05 —81.88.7 deepseek/deepseek-v4-flash-0731 DeepSeek · 2026-07-31 —8117.1 thinkingmachines/inkling-small ThinkingMachines · 2026-07-30 —95.217 qwen/qwen3.7-flash Qwen · 2026-07-27 —76.215.7 anthropic/claude-opus-5 Anthropic · 2026-07-24 67.777.819.7 google/gemini-3.6-flash Google · 2026-07-21 69.878.621 google/gemini-3.6-flash-lite Google · 2026-07-21 ——— thinkingmachines/inkling ThinkingMachines · 2026-07-17 6485.725.2 meta/muse-spark-1.1 Meta · 2026-07-16 73.4696.5 moonshotai/kimi-k3 MoonshotAI · 2026-07-16 65.87624.2 openai/gpt-5.6-luna OpenAI · 2026-07-09 69.771.716.7 openai/gpt-5.6-sol OpenAI · 2026-07-09 79.872.718.5 openai/gpt-5.6-terra OpenAI · 2026-07-09 67.978.721.1 x-ai/grok-4.5 xAI · 2026-07-08 69.872.92.3 anthropic/claude-sonnet-5 Anthropic · 2026-06-30 70.877.321.4 tencent/hy3 Tencent · 2026-06-26 65.876.914 sakana/fugu-ultra Sakana · 2026-06-23 65.98613.6 z-ai/glm-5.2 Z.ai · 2026-06-16 61.686.426.7 moonshotai/kimi-k2.7-code MoonshotAI · 2026-06-12 67.588.618.5 anthropic/claude-fable-5 Anthropic · 2026-06-09 73.582.219.4 nvidia/nemotron-3-ultra-550b-a55b NVIDIA · 2026-06-04 68.88031.8 qwen/qwen3.7-plus Qwen · 2026-06-03 65.780.524 minimax/minimax-m3 MiniMax · 2026-05-31 6181.421.4 stepfun/step-3.7-flash StepFun · 2026-05-28 57.270.724.3 anthropic/claude-opus-4.8 Anthropic · 2026-05-27 75.182.623.5 qwen/qwen3.7-max Qwen · 2026-05-21 65.184.119.1 google/gemini-3.5-flash Google · 2026-05-19 81.689.726.6 google/gemini-3.1-flash-lite Google · 2026-05-07 80.388.922.8 ibm-granite/granite-4.1-8b IBM · 2026-04-30 7162.122.9 x-ai/grok-4.3 xAI · 2026-04-30 70756.6 qwen/qwen3.6-27b Qwen · 2026-04-26 65.470.514.9 qwen/qwen3.6-flash Qwen · 2026-04-26 62.776.112.8 qwen/qwen3.6-max-preview Qwen · 2026-04-26 76.884.48.8 openai/gpt-5.5 OpenAI · 2026-04-24 72.976.116.8 deepseek/deepseek-v4-flash DeepSeek · 2026-04-23 59.576.613 deepseek/deepseek-v4-pro DeepSeek · 2026-04-23 61.9837.9 xiaomi/mimo-v2.5 Xiaomi · 2026-04-22 56.18026.8 xiaomi/mimo-v2.5-pro Xiaomi · 2026-04-22 53.580.418.1 moonshotai/kimi-k2.6 MoonshotAI · 2026-04-20 72.180.521.8 anthropic/claude-opus-4.7 Anthropic · 2026-04-16 75.779.210.5 z-ai/glm-5.1 Z.ai · 2026-04-07 64.781.819.8 google/gemma-4-26b-a4b-it Google · 2026-04-03 74.481.839.9 google/gemma-4-31b-it Google · 2026-04-02 72.283.833.4 qwen/qwen3.6-plus Qwen · 2026-04-02 65.279.510.8 x-ai/grok-4.20 xAI · 2026-03-31 64.360.46.1 minimax/minimax-m2.7 MiniMax · 2026-03-18 59.578.627.7 openai/gpt-5.4-mini OpenAI · 2026-03-17 64.58318.3 openai/gpt-5.4-nano OpenAI · 2026-03-17 58.963.320.1 mistralai/mistral-small-2603 Mistral · 2026-03-16 64.967.411.3 z-ai/glm-5-turbo Z.ai · 2026-03-15 67.877.316.8 nvidia/nemotron-3-super-120b-a12b NVIDIA · 2026-03-11 ——— bytedance-seed/seed-2.0-lite Bytedance · 2026-03-10 ——36.1 openai/gpt-5.4 OpenAI · 2026-03-05 72.568.915.5 inception/mercury-2 Inception · 2026-03-04 59.266.121.5 openai/gpt-5.3-chat OpenAI · 2026-03-03 59.178.417.3 qwen/qwen3.5-122b-a10b Qwen · 2026-02-25 71.181.124.3 qwen/qwen3.5-flash-02-23 Qwen · 2026-02-25 67.179.531 anthropic/claude-sonnet-4.6 Anthropic · 2026-02-17 71.368.220.6 minimax/minimax-m2.5 MiniMax · 2026-02-12 5975.625.7 z-ai/glm-5 Z.ai · 2026-02-11 69.182.935.1 anthropic/claude-opus-4.6 Anthropic · 2026-02-04 72.371.127.5 upstage/solar-pro-3 Upstage · 2026-01-27 46.956.717.9 moonshotai/kimi-k2.5 MoonshotAI · 2026-01-26 66.988.615.7 z-ai/glm-4.7-flash Z.ai · 2026-01-19 54.98531.7 bytedance-seed/seed-1.6 Bytedance · 2025-12-23 ——33.9 bytedance-seed/seed-1.6-flash Bytedance · 2025-12-23 —71.421.8 minimax/minimax-m2.1 MiniMax · 2025-12-22 59.574.430.2 z-ai/glm-4.7 Z.ai · 2025-12-21 66.294.722.9 google/gemini-3-flash-preview Google · 2025-12-17 78.482.923.3 nvidia/nemotron-3-nano-30b-a3b NVIDIA · 2025-12-14 ——— amazon/nova-2-lite-v1 Amazon · 2025-12-02 —7029.6 deepseek/deepseek-v3.2 DeepSeek · 2025-12-01 6579.519.8 anthropic/claude-haiku-4.5 Anthropic · 2025-10-15 74.365.926.7 anthropic/claude-sonnet-4.5 Anthropic · 2025-09-29 7178.627.4 openai/gpt-oss-120b OpenAI · 2025-08-05 6270.218.1 google/gemini-2.5-flash-lite Google · 2025-07-22 65.885.418 qwen/qwen3-235b-a22b-2507 Qwen · 2025-07-21 6367.416.9 mistralai/mistral-small-3.2-24b-instruct Mistral · 2025-06-20 71.77017.6 google/gemini-2.5-flash Google · 2025-06-17 73.57518.9 openai/o3 OpenAI · 2025-04-16 —77.38.7 openai/o4-mini OpenAI · 2025-04-16 —68.25.7 openai/gpt-4.1 OpenAI · 2025-04-14 —85.79.2 openai/gpt-4.1-mini OpenAI · 2025-04-14 70.179.526.3 openai/gpt-4.1-nano OpenAI · 2025-04-14 ——23.9 meta-llama/llama-4-maverick Meta · 2025-04-05 —60.92.5 meta-llama/llama-4-scout Meta · 2025-04-05 —66.713.8 deepseek/deepseek-chat-v3-0324 DeepSeek · 2025-03-24 —708.8 openai/o3-mini OpenAI · 2025-01-31 —71.48.2 mistralai/mistral-small-24b-instruct-2501 Mistral · 2025-01-30 ——21.8 deepseek/deepseek-r1 DeepSeek · 2025-01-20 —61.93.2 meta-llama/llama-3.3-70b-instruct Meta · 2024-12-06 —60.90 amazon/nova-lite-v1 Amazon · 2024-12-05 —7026.1 amazon/nova-micro-v1 Amazon · 2024-12-05 ——27 meta-llama/llama-3.1-70b-instruct Meta · 2024-07-22 —59.13 meta-llama/llama-3.1-8b-instruct Meta · 2024-07-22 —5015.8 mistralai/mistral-nemo Mistral · 2024-07-18 7571.15 openai/gpt-4o-mini OpenAI · 2024-07-17 71.573.221.5 google/gemma-2-27b-it Google · 2024-07-12 ——29.6 anthropic/claude-3-haiku Anthropic · 2024-03-12 —52.410 mistralai/mistral-large Mistral · 2024-02-25 —61.914.8 openai/gpt-3.5-turbo-instruct OpenAI · 2023-09-27 ——— openai/gpt-3.5-turbo OpenAI · 2023-05-27 —72.718.2 openai/gpt-4 OpenAI · 2023-05-27 ——26.1
No models match.