UnifyBench

RankingAgents' Last Exam

Agents' Last Exam

Data updated 6 Oct 2026

Bucket
Supporting evidence
Unit
percent
Direction
Higher is better
Version
2026-10-05
Display harness
Agents' Last Exam · Claude Code
Board
https://agents-last-exam.org/leaderboard

Agents' Last Exam score is the Full/Overall pass rate. One row per model and harness at the board's default effort. Display only. These rows do not enter the weighted Overall or capability scores.

Compare published benchmark results with category weights →

Models

Results are ordered by score in the display harness, followed by models with no result. Other harnesses are listed separately below. Missing results remain unknown.

126–150 of 460 entries

ModelScoreEvidenceSource-recorded date
Gemma 1 7B ITGoogle———
Gemma 1.1 2B ITGoogle———
Gemma 1.1 7B ITGoogle———
Gemma 2 27B ITGoogle———
Gemma 2 2B ITGoogle———
Gemma 2 9B ITGoogle———
Gemma 3 12B ITGoogle———
Gemma 3 1B ITGoogle———
Gemma 3 270M ITGoogle———
Gemma 3 27B ITGoogle———
Gemma 3 4B ITGoogle———
Gemma 3n E2B ITGoogle———
Gemma 3n E4B ITGoogle———
Gemma 4 12B ITGoogle———
Gemma 4 26B-A4B ITGoogle———
Gemma 4 31B ITGoogle———
Gemma 4 E2B ITGoogle———
Gemma 4 E4B ITGoogle———
GLM-4-32B-0414Z.ai———
GLM-4-32B-0414-128KZ.ai———
GLM-4-9B-0414Z.ai———
glm-4-9b-chatZ.ai———
glm-4-9b-chat-1mZ.ai———
GLM-4.1V-9B-ThinkingZ.ai———
GLM-4.5Z.ai———

Other harnesses

These runs use other harnesses. Capability scoring matches configurations separately; model details identify which source records contribute.

ModelScoreHarnessEvidenceSource-recorded date
Claude Opus 4.7Anthropic18.4%Agents' Last Exam · ALE-Clawofficial board2026-10-06
Claude Opus 4.7Anthropic21.1%Agents' Last Exam · Cursor CLIofficial board2026-10-06
Claude Opus 4.7Anthropic13.5%Agents' Last Exam · Droidofficial board2026-10-06
Claude Opus 4.7Anthropic15.8%Agents' Last Exam · OpenClawofficial board2026-10-06
Gemini 3.1 ProGoogle16.4%Agents' Last Exam · Gemini CLIofficial board2026-10-06
Gemini 3.1 ProGoogle14.1%Agents' Last Exam · OpenClawofficial board2026-10-06
GLM-5.1Z.ai11.5%Agents' Last Exam · OpenClawofficial board2026-10-06
GPT-5.4OpenAI11.8%Agents' Last Exam · ALE-Clawofficial board2026-10-06
GPT-5.4OpenAI20.5%Agents' Last Exam · OpenClawofficial board2026-10-06
GPT-5.5OpenAI23%Agents' Last Exam · ALE-Clawofficial board2026-10-06
GPT-5.5OpenAI26.6%Agents' Last Exam · Codexofficial board2026-10-06
GPT-5.5OpenAI21.4%Agents' Last Exam · Cursor CLIofficial board2026-10-06
GPT-5.5OpenAI19.7%Agents' Last Exam · Droidofficial board2026-10-06
GPT-5.5OpenAI21.7%Agents' Last Exam · OpenClawofficial board2026-10-06
GPT-5.6 LunaOpenAI30.3%Agents' Last Exam · Codexofficial board2026-10-06
GPT-5.6 SolOpenAI30.6%Agents' Last Exam · Codexofficial board2026-10-06
GPT-5.6 TerraOpenAI28%Agents' Last Exam · Codexofficial board2026-10-06
GPT-6 AstraOpenAI34.2%Agents' Last Exam · Codexofficial board2026-10-06
GPT-6 LunaOpenAI25%Agents' Last Exam · Codexofficial board2026-10-06
GPT-6 SolOpenAI32.2%Agents' Last Exam · Codexofficial board2026-10-06
Grok-4.3xAI7.2%Agents' Last Exam · Grok CLIofficial board2026-10-06
Grok-4.3xAI4.3%Agents' Last Exam · OpenClawofficial board2026-10-06
Grok-4.5xAI27%Agents' Last Exam · Grok Buildofficial board2026-10-06
Kimi K3Moonshot28.3%Agents' Last Exam · Kimi Codeofficial board2026-10-06
Kimi-K2.6Moonshot9.2%Agents' Last Exam · OpenClawofficial board2026-10-06
MiMo-V2.5Xiaomi8.6%Agents' Last Exam · OpenClawofficial board2026-10-06
MiniMax-M2.7MiniMax5.9%Agents' Last Exam · OpenClawofficial board2026-10-06
Muse Spark 1.3Meta32.2%Agents' Last Exam · Codexofficial board2026-10-06
Qwen3.6-plusQwen8.6%Agents' Last Exam · OpenClawofficial board2026-10-06
Qwen3.7-maxQwen11.8%Agents' Last Exam · OpenClawofficial board2026-10-06