CtrlAltDebrief

AI model benchmarks

25 benchmarks across reasoning, maths, coding and agentic tasks. Each one ranks every model that carries a score and puts its API cost alongside, where it has one.

Benchmarks

25

leaderboards

Categories

5

reasoning · maths · coding · agents

Models ranked

453

on the widest board

Source

AA + HF

verified daily

Headline indices

3 benchmarks
Intelligence IndexComposite
453 models ranked
  1. 1Claude Opus 563.1
  2. 2Claude Fable 562.1
  3. 3GPT-5.6 Sol60.9
View full leaderboard →
Coding IndexComposite
184 models ranked
  1. 1GPT-5.6 Sol78.3
  2. 2Claude Opus 578.0
  3. 3Grok 4.676.8
View full leaderboard →
Agentic IndexComposite
159 models ranked
  1. 1Claude Opus 559.2
  2. 2GLM 5.359.1
  3. 3Grok 4.658.7
View full leaderboard →

Reasoning & knowledge

7 benchmarks
GPQA Diamond
441 models ranked
  1. 1Grok 4.695%
  2. 2Gemini 3.7 Flash95%
  3. 3Gemini 3.1 Pro Preview94%
View full leaderboard →
Humanity's Last Exam
430 models ranked
  1. 1Claude Fable 555%
  2. 2Claude Opus 555%
  3. 3GPT-5.6 Sol49%
View full leaderboard →
CritPt
349 models ranked
  1. 1GPT-5.6 Sol32%
  2. 2GPT-5.5 Pro31%
  3. 3GPT-5.6 Terra30%
View full leaderboard →
Omniscience
347 models ranked
  1. 1Claude Fable 543.3
  2. 2Claude Opus 537.1
  3. 3Gemini 3.1 Pro Preview31.9
View full leaderboard →
MMLU-Pro
269 models ranked
  1. 1Gemini 3 Pro90%
  2. 2Claude Opus 4.589%
  3. 3Gemini 3 Flash89%
View full leaderboard →
MMMU-Pro
151 models ranked
  1. 1Gemini 3.7 Flash85%
  2. 2Claude Opus 585%
  3. 3Gemini 3.5 Flash84%
View full leaderboard →
ARC-AGI-2
61 models ranked
  1. 1GPT-5.6 Sol93%
  2. 2GPT-5.585%
  3. 3GPT-5.5 Pro85%
View full leaderboard →

Math

1 benchmarks
AIME 2026
20 models ranked
  1. 1Inkling97%
  2. 2A.X-K297%
  3. 3Step 3.5 Flash97%
View full leaderboard →

Coding & agents

12 benchmarks
SciCode
428 models ranked
  1. 1Claude Fable 560%
  2. 2Gemini 3.1 Pro Preview59%
  3. 3Kimi K359%
View full leaderboard →
τ²-bench
314 models ranked
  1. 1GLM 5.299%
  2. 2JT-35B-Flash99%
  3. 3GLM 4.7 Flash99%
View full leaderboard →
TerminalBench Hard
308 models ranked
  1. 1GPT-5.6 Sol66%
  2. 2Claude Fable 563%
  3. 3GPT-5.6 Terra63%
View full leaderboard →
LiveCodeBench
266 models ranked
  1. 1Gemini 3 Pro92%
  2. 2Gemini 3 Flash91%
  3. 3DeepSeek V3 2 Speciale90%
View full leaderboard →
TerminalBench v2.1
165 models ranked
  1. 1GPT-5.6 Sol90%
  2. 2Claude Opus 589%
  3. 3Grok 4.688%
View full leaderboard →
τ-bench Banking
165 models ranked
  1. 1Qwen3.8 Max51%
  2. 2Grok 4.651%
  3. 3GLM 5.350%
View full leaderboard →
GDPval
162 models ranked
  1. 1Claude Opus 51844.7
  2. 2Grok 4.61747.5
  3. 3Claude Fable 51737.7
View full leaderboard →
SWE-bench Verified
39 models ranked
  1. 1Macaron V1 Venti86%
  2. 2DeepSeek V4 Pro 042381%
  3. 3MiniMax M381%
View full leaderboard →
IT-Bench SRE
35 models ranked
  1. 1GPT-5.6 Sol56%
  2. 2GPT-5.6 Terra51%
  3. 3Kimi K348%
View full leaderboard →
SWE-bench Pro
33 models ranked
  1. 1Qwen3.8 2.4T A95B68%
  2. 2Hy4 preview66%
  3. 3Qwen3.8-Flash-Next63%
View full leaderboard →
APEX Agents
31 models ranked
  1. 1Gemini 3.5 Flash47%
  2. 2Kimi K341%
  3. 3GPT-5.6 Terra39%
View full leaderboard →
AA-Briefcase
24 models ranked
  1. 1Claude Fable 554%
  2. 2Claude Sonnet 545%
  3. 3Claude Opus 4.843%
View full leaderboard →

Instruction & long-context

2 benchmarks
Long-Context ReasoningComposite
364 models ranked
  1. 1Muse Spark 1.283%
  2. 2Kimi K383%
  3. 3Muse Spark 1.181%
View full leaderboard →
IFBench
321 models ranked
  1. 1Grok 4.383%
  2. 2Grok 4.20 030983%
  3. 3MiniMax M383%
View full leaderboard →
Benchmark scores via ARC Prize, Artificial Analysis and Hugging Face leaderboards · pricing verified against LiteLLM + OpenRouter · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI