AI Benchmark Leaderboard

Compare AI model scores, coding ability and performance in one place.

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
26 Claude Sonnet 5.5 (Xhigh, Default Fallback) Anthropic 49.9 ——————————
27 Claude Fable 5.1 (Max, Default Fallback) Anthropic 49.2 ——————————
28 Claude Opus 5.5 (Medium, Default Fallback) Anthropic 48.2 ——————————
29 Gemini 4 Argon (Medium) Google 47.6 ——————————
30 Claude Fable 5.1 (High, Default Fallback) Anthropic 47.2 ——————————
31 Kimi K3.1 Pro Kimi 46.5 ——————————
32 GPT-6.1 Sol (Medium) OpenAI 46.3 ——————————
33 GPT-6.1 Terra (Xhigh) OpenAI 45.3 ——————————
34 GPT-6 Astra (Non-reasoning) OpenAI 45.2 76.2 —— 89.5 ——— 53.5 — 37.1
35 Claude Opus 5 (Max) Anthropic 44.2 ——————————
36 GPT-6 Sol (Max) OpenAI 44.2 ——————————
37 Muse Wonder (Max) Meta 43.6 ——————————
38 GPT-6 Astra (Low) OpenAI 43.3 ——————————
39 Claude Fable 5.1 (Medium, Default Fallback) Anthropic 43.2 ——————————
40 Qwen4 Max Alibaba 42.9 ——————————
41 GPT-6.1 Terra (High) OpenAI 42.4 ——————————
42 Claude Sonnet 5.5 (High, Default Fallback) Anthropic 41.5 ——————————
43 Gemini 4 Hydrogen (Medium) Google 41.2 ——————————
44 Muse Wonder (High) Meta 40.5 ——————————
45 Claude Fable 5.1 (Low, Default Fallback) Anthropic 38.7 ——————————
46 GPT-6.1 Terra (Medium) OpenAI 38.2 ——————————
47 DeepSeek V4 Flash (Reasoning, High Effort) DeepSeek 37.5 52.0 —— 86.7 ——— 42.0 73.5 27.8
48 Muse Spark 1.3 (Max) Meta 36.6 ——————————
49 Claude Haiku 5.5 (Max) Anthropic 36.5 ——————————
50 Doubao Seed 2.0 lite (Reasoning) ByteDance Seed 36.3 21.4 —— 65.6 ——— 24.7 61.2 22.0

AI Benchmarks FAQ

Which AI model is best for my task?

Compare the scores most relevant to your task, then consider speed, pricing and practical requirements. A high score in one benchmark does not make a model the best choice for every use.

What does a missing benchmark score mean?

A dash means that a score is not available for that model in this table. It should not be treated as a score of zero.

How are the top models ranked?

By the intelligence index, highest first. The Top models cards show the eight highest-scoring current models, one per model family, and models with the same score share a place.

Where do the scores come from?

From independent third-party model evaluations, which Franklin AI syncs automatically each day. Each model page links to About these benchmarks, which explains them in more detail.

What does a model page show?

Its scores, its price per million input and output tokens, its measured speed and comparisons with other models, where that data is available.