Benchmark Almanac

Epoch Automation Reports

Claude Fable 5.1 65.3% leads since Oct 2026 Not in model cards

Agents in coding harnesses do real Epoch AI work tasks such as graphic design, data insights and research design. Epoch staff grade outputs against the rubric they use for employees.

Six systems in the first release on 2026-10-08. Claude Fable 5.1 and GPT-6 Astra lead at 65% mean rubric score.

Made by Epoch AI Released Oct 2026 Simulated companies Tasks kept private Last model added Sep 2026 Scores refreshed 2 Nov 2026
Level
Expert Specialists with years of training, often over hours of work
Scored
Graded by people Human experts grade or compare the outputs.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Paper Leaderboard epoch.ai
6
Models scored on its own leaderboard

Claude Fable 5.1 leads with 65.3% among models released by Sep 2026

Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in Sep 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 65.3 Claude Fable 5.1
  2. 65.1 GPT-6 Astra
  3. 59.1 Grok 4.6
  4. 53.0 Qwen 3.8 Max
  5. 52.4 Kimi K3
  6. 42.3 Gemini 3.8 Flash
  1. 1 Claude Fable 5.1 65.3%
  2. 2 GPT-6 Astra 65.1%
  3. 3 Grok 4.6 59.1%
  4. 4 Qwen 3.8 Max 53%
  5. 5 Kimi K3 52.4%
  6. 6 Gemini 3.8 Flash 42.3%
#ModelScoreSettingDateSource
1 Claude Fable 5.1 65.3% Claude Code Sep 2026 Official leaderboard
2 GPT-6 Astra 65.1% Codex Sep 2026 Official leaderboard
3 Grok 4.6 59.1% Grok Build Aug 2026 Official leaderboard
4 Qwen 3.8 Max 53% Qwen Code Aug 2026 Official leaderboard
5 Kimi K3 52.4% Kimi Code Jul 2026 Official leaderboard
6 Gemini 3.8 Flash 42.3% Antigravity Sep 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard 1 leader
Claude Fable 5.1 65.3%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Fable 5.1 Grok 4.6 Qwen 3.8 Max 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Claude Fable 5.1 Qwen 3.8 Max

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Economic work

All 91 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Qwen3.8-Omni-Flash 75.3%
  • OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%