Acme Agent Evals
Agents use GitHub tools to answer questions about issues, pull requests, and code in a simulated software project.
Arize reports model comparisons in its article.
- Made by
- Arize AI
- Released
- May 2026
- Kind
- Apps and MCP servers
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Claude Sonnet 4.6 leads with 85.1% among models released by April 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Claude Sonnet 4.6 85.1%
- 2 Claude Sonnet 4 83.5%
- 3 Claude Sonnet 4.5 83.4%
- 4
Gemini 3 Flash 82.3%
- 5
Gemini 3.1 Pro 81.1%
- 6 GPT-5.5 80.5%
- 7 GPT-5 79.6%
Source: Official Acme Agent Evals leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 85.1% | Pi | Feb 2026 | Official leaderboard |
| 2 | Claude Sonnet 4 | 83.5% | Pi | May 2025 | Official leaderboard |
| 3 | Claude Sonnet 4.5 | 83.4% | Pi | Sep 2025 | Official leaderboard |
| 4 | | 82.3% | Pi | Dec 2025 | Official leaderboard |
| 5 | | 81.1% | Pi | Feb 2026 | Official leaderboard |
| 6 | GPT-5.5 | 80.5% | Pi | Apr 2026 | Official leaderboard |
| 7 | GPT-5 | 79.6% | Pi | Aug 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Acme Agent Evals leaderboard
Claude Sonnet 4.6 on the official leaderboard passed 85% in February 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Acme Agent Evals leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More 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 Neon 56.3%
- 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%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Note Newest score The newest came 7 months ago, in April 2026, for GPT-5.5. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.5 (#21).
- Note Headroom Saturated. The best is 85.1%, past 85% since February 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on arize.com: 14 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.