activeAgents

Agents' Last Exam

Metric: Score (higher is better)Introduced: 2026

Multi-domain agentic reasoning benchmark spanning professional long-horizon workflows. OpenAI's GPT-5.6 launch reports standard-mode scores; preserve harness and mode labels because code-mode and standard-mode rows are not directly comparable.

Models ranked

12

tracked on this benchmark

Score band

75.8 – 26.3

best → lowest tracked

Snapshot trend

+32.60

Oct 23 → Nov 18 · 1 models

Leaderboard

Tracked models ranked by Score (higher is better).

Compare candidates
#Model variant and provenanceScore
1

Configuration: Agents' Last Exam v1.1; Antigravity-CLI 1.4.8; 122-task; 5-hour window; safety filters enabled; averaged rubric score

Version: Agents' Last Exam v1.1Harness: Self-computed on the 122-task v1.1 benchmark using the Antigravity-CLI version 1.4.8 harness through official integration and a 5-hour window, with safety filters enabled; averaged rubric scoreEvaluator: Google DeepMindObserved: Nov 18, 2026Confidence: self-reportedSource

Notes: Google DeepMind model card results table (as of November 2026): Agents' Last Exam v1.1 75.8%. Evals methodology records the self-computed harness above. Timestamp is retrieval date.

75.8
2

Configuration: gpt-6.1-terra (Max)

Version: Agents' Last Exam v1 (OpenAI launch chart); max reasoning effortHarness: Not stated in the launch postEvaluator: OpenAIObserved: Oct 26, 2026Confidence: self-reportedSource

Notes: OpenAI launch post chart 'Agents’ Last Exam v1' (Max 0.600; Low 0.559, Medium 0.576, High 0.572, Xhigh 0.585). Chart is labelled v1; the official ALE board shows v1.1 and did not list GPT-6.1 Terra at capture. Retrieved 2026-10-26.

60.0
3
Version: OpenAI launch table; professional long-horizon workflows; standard modeHarness: Not recordedEvaluator: Not recordedObserved: Jul 9, 2026Confidence: Not recordedSource

Notes: Official GPT-5.6 GA launch benchmark row.

52.7
4
Version: Agents' Last Exam v1.1 (ALL, 122 tasks); max reasoning effortHarness: Not recordedEvaluator: Not recordedObserved: Oct 23, 2026Confidence: Not recordedSource

Notes: Moonshot self-reported launch table, row 'Agents' Last Exam (ALL)', column 'Kimi K3.1 Pro (max)'. Settings: reasoning effort max, temperature 1.0, top-p 0.95 (blog footnote).

43.2
5

Configuration: Gemini 4 Argon

Version: Agents' Last Exam (binary pass rate)Harness: ALE-Claw (default harness)Evaluator: Google DeepMindObserved: Oct 17, 2026Confidence: self-reportedSource

Notes: Blog table + methodology page: binary pass rate, ALE-Claw default harness, 5-hour window, safety filters on. Retrieved 2026-10-17.

39.5
6
Version: Agents' Last ExamHarness: Not recordedEvaluator: Not recordedObserved: Oct 17, 2026Confidence: Not recordedSource
35.4
7
Version: Agent's Last Exam Pass@1; official scaffold; max reasoning effortHarness: Not recordedEvaluator: Not recordedObserved: Sep 10, 2026Confidence: Not recordedSource
31.8
8
Version: Agents' Last ExamHarness: Not recordedEvaluator: Not recordedObserved: Oct 9, 2026Confidence: Not recordedSource
31.6
9

Configuration: minimax-m3-1-flash (Max)

Version: Agents' Last Exam, official Overall full set (binary pass rate)Harness: Claude CodeEvaluator: Agents' Last Exam (official leaderboard)Observed: Oct 19, 2026Confidence: confirmedSource

Notes: Official ALE leaderboard (benchmark owner; headless-Chrome DOM): row 'Claude Code | minimax-m3-1-flash | Max | 29.6% | 55.0%' (Pass Rate 29.6%, Score 55.0%). Matches MiniMax blog (29.6, 'official Overall setting'). A Codex-harness row for the same model shows 27.0% (not packed; highest official entry used, same as blog). Retrieved 2026-10-19.

29.6
10
Version: Agents' Last Exam (CLI)Harness: Not recordedEvaluator: Not recordedObserved: Aug 14, 2026Confidence: Not recordedSource
28.5
11
Version: Agents' Last ExamHarness: Not recordedEvaluator: Not recordedObserved: Oct 9, 2026Confidence: Not recordedSource
27.6
12
Version: Agents' Last Exam (CLI)Harness: Not recordedEvaluator: Not recordedObserved: Aug 26, 2026Confidence: Not recordedSource
26.3

How to read this benchmark

This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.

Trust this score when

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

Related benchmarks

Last reviewed: Jul 9, 2026

Resources