Benchmark Almanac

The Amazing Agent Race

Claude Sonnet 4 36.6% leads since April 2026
Not in model cards

Agents navigate websites, call tools, and calculate a passcode across 1,400 scavenger hunts. The benchmark includes 800 sequential puzzles and 600 with branching paths.

Claude Code with Claude Sonnet 4 led GPT-5.4 and GPT-5.4 mini configurations with 36.6% final accuracy in April 2026.

Made by
Minnesota NLP
Released
April 2026
Kind
Function calling
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
APIs and tools, Browser
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
3
Models scored on its own leaderboard

Claude Sonnet 4 leads with 36.6% among models released by March 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 March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Sonnet 4 36.6%
  2. 2 GPT-5.4 34.8%
  3. 3 GPT-5.4 Mini 32.1%

Source: Official The Amazing Agent Race leaderboard

#ModelScoreSettingDateSource
1 Claude Sonnet 4 36.6% Claude Code May 2025 Official leaderboard
2 GPT-5.4 34.8% Codex CLI Mar 2026 Official leaderboard
3 GPT-5.4 Mini 32.1% Codex CLI Mar 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

Source: Official The Amazing Agent Race leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Sonnet 4 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Sonnet 4

Source: Official The Amazing Agent Race 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

All 265 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 8 months ago, in March 2026, for GPT-5.4 Mini. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored Only 3 models we track.
  • Warning Newest score The newest came 8 months ago, in March 2026, for GPT-5.4 Mini.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
  • Pass Headroom The best is 36.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on minnesotanlp.github.io: 5 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.

How we check