Benchmark Almanac

Gaia2-CLI

Claude Opus 4.6 57% leads since April 2026
Not in model cards

Agents complete realistic tasks through command-line tools. The benchmark measures task success across search, execution, adaptability, ambiguity, and time constraints.

CLI task-set scores remain separate from legacy Gaia2. The official board identifies the OpenClaw harness and reasoning settings.

Made by
Meta FAIR
Released
April 2026
Kind
General assistants
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-5.5 #20 on the capability index
Last model added
April 2026
Scores refreshed
November 12th, 2026
7
Models scored on its own leaderboard

Claude Opus 4.6 leads with 57% among models released by April 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

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

  1. 57.0 Claude Opus 4.6
  2. 56.4 GPT-5.5
  3. 55.6 GPT-5.4
  4. 52.0 Gemini 3.1 Pro
  5. 51.9 Claude Sonnet 4.6
  6. 50.5 GLM-5.1
  7. 34.0 Kimi K2.5
  1. 1 Claude Opus 4.6 high 57%
  2. 2 GPT-5.5 xhigh 56.4%
  3. 3 GPT-5.4 high 55.6%
  4. 4 Gemini 3.1 Pro high 52%
  5. 5 Claude Sonnet 4.6 high 51.9%
  6. 6 GLM-5.1 enabled 50.5%
  7. 7 Kimi K2.5 enabled 34%

Source: Official Gaia2-CLI leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 4.6 57% high, OpenClaw 2026.4.1 Feb 2026 Official leaderboard
2 GPT-5.5 56.4% xhigh, OpenClaw 2026.4.1 Apr 2026 Official leaderboard
3 GPT-5.4 55.6% high, OpenClaw 2026.4.1 Mar 2026 Official leaderboard
4 Gemini 3.1 Pro 52% high, OpenClaw 2026.4.1 Feb 2026 Official leaderboard
5 Claude Sonnet 4.6 51.9% high, OpenClaw 2026.4.1 Feb 2026 Official leaderboard
6 GLM-5.1 50.5% enabled, OpenClaw 2026.4.1 Apr 2026 Official leaderboard
7 Kimi K2.5 34% enabled, OpenClaw 2026.4.1 Jan 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 Not tested since Apr 2026
Claude Opus 4.6 57%

Source: Official Gaia2-CLI leaderboard

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% 2026 Near the ceiling (85%) Claude Opus 4.6 Kimi K2.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 Kimi K2.5

Source: Official Gaia2-CLI leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Tool use

All 144 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Carbon 53.9%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%