WorkflowArena
Agents write executable workflows that coordinate other agents on professional tasks. Hidden verifiers check the completed deliverables.
The overall resolved rate averages the eight domain rates equally. Each task requires every acceptance criterion to pass.
- Made by
- Navers Lab, Einsia.AI and Tsinghua University
- Released
- November 2026
- Kind
- Multi-agent games
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Computer and information sciences, Mathematics, Law, Arts
- Language
- English
- Interaction
- Multi-agent
- Environment
- Terminal
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Image, video and 3D generation, Law and finance
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 37% among models released by September 2026 Claude Opus 5.5 leads with 37% among models released by September 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Claude Code + Kimi K3.1 Pro, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in September 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-6.1 Terra
- and 12 more
- 1 Claude Opus 5.5 max 37%
- 2 Claude Sonnet 5.5 max 33.2%
- 3 GPT-6 Astra xhigh 30.8%
- 4 GPT-6.1 Sol xhigh 29.5%
- 5 Claude Code + Kimi K3.1 Pro max 16.5%
- 6 GPT-6 Luna max 13.3%
- 7 Claude Code + Doubao Seed Evolving Nov 2026, high 10.8%
- 8 Claude Code + DeepSeek V4.1 Flash max 6.08%
- 9 Claude Code + GLM-5.3-Flash max 4.43%
Source: The WorkflowArena paper
- 1 Claude Opus 5.5 max 37%
- 2 Claude Sonnet 5.5 max 33.2%
- 3 GPT-6 Astra xhigh 30.8%
- 4 GPT-6.1 Sol xhigh 29.5%
- 5 GPT-6 Luna max 13.3%
Source: The WorkflowArena paper
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 37% | max, Claude Code | Sep 2026 | Nov 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 33.2% | max, Claude Code | Sep 2026 | Nov 2026 | Official leaderboard |
| 3 | GPT-6 Astra | 30.8% | xhigh, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 29.5% | xhigh, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
| 5 | Claude Code + Kimi K3.1 Pro | 16.5% | max | Oct 2026 | Nov 2026 | Official leaderboard |
| 6 | GPT-6 Luna | 13.3% | max, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
| 7 | Claude Code + Doubao Seed Evolving Nov 2026 | 10.8% | high | Nov 2026 | Nov 2026 | Official leaderboard |
| 8 | Claude Code + DeepSeek V4.1 Flash | 6.08% | max | Sep 2026 | Nov 2026 | Official leaderboard |
| 9 | Claude Code + GLM-5.3-Flash | 4.43% | max | Aug 2026 | Nov 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 37% | max, Claude Code | Sep 2026 | Nov 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 33.2% | max, Claude Code | Sep 2026 | Nov 2026 | Official leaderboard |
| 3 | GPT-6 Astra | 30.8% | xhigh, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 29.5% | xhigh, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
| 5 | GPT-6 Luna | 13.3% | max, Codex | Sep 2026 | Nov 2026 | Official leaderboard |
Rankings by part
We read 16 parts from the benchmark’s paper in 2 groups: resolved rate and continuous score. Each ranks models on one part of the test. Claude Opus 5.5 leads 12 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Software & systems
5 models we track have a score here.
- 1 Claude Opus 5.5 29.4%
- 2 Claude Sonnet 5.5 11.8%
- 3 GPT-6 Astra 5.88%
- 4 GPT-6 Luna ↑1 0%
- 5 GPT-6.1 Sol ↓1 0%
Enterprise operations
5 models we track have a score here.
- 1 GPT-6 Astra ↑2 27.8%
- 2 Claude Opus 5.5 ↓1 22.2%
- 3 GPT-6.1 Sol ↑1 22.2%
- 4 Claude Sonnet 5.5 ↓2 11.1%
- 5 GPT-6 Luna 5.56%
Science
5 models we track have a score here.
- 1 Claude Opus 5.5 56.3%
- 2 GPT-6 Astra ↑1 50%
- 3 Claude Sonnet 5.5 ↓1 50%
- 4 GPT-6.1 Sol 43.8%
- 5 GPT-6 Luna 37.5%
Formal mathematics
5 models we track have a score here.
- 1 Claude Opus 5.5 95.8%
- 2 GPT-6 Astra ↑1 83.3%
- 3 GPT-6.1 Sol ↑1 83.3%
- 4 Claude Sonnet 5.5 ↓2 79.2%
- 5 GPT-6 Luna 25%
Finance
5 models we track have a score here.
- 1 Claude Opus 5.5 18.8%
- 2 Claude Sonnet 5.5 18.8%
- 3 GPT-6.1 Sol ↑1 18.8%
- 4 GPT-6 Astra ↓1 12.5%
- 5 GPT-6 Luna 12.5%
Law
5 models we track have a score here.
- 1 Claude Sonnet 5.5 ↑1 9.09%
- 2 GPT-6 Astra ↑1 4.55%
- 3 Claude Opus 5.5 ↓2 4.55%
- 4 GPT-6 Luna ↑1 4.55%
- 5 GPT-6.1 Sol ↓1 4.55%
Content design
5 models we track have a score here.
- 1 Claude Sonnet 5.5 ↑1 64.3%
- 2 GPT-6 Astra ↑1 57.1%
- 3 Claude Opus 5.5 ↓2 57.1%
- 4 GPT-6.1 Sol 57.1%
- 5 GPT-6 Luna 21.4%
3D production
5 models we track have a score here.
- 1 Claude Opus 5.5 27.8%
- 2 Claude Sonnet 5.5 27.8%
- 3 GPT-6.1 Sol ↑1 22.2%
- 4 GPT-6 Astra ↓1 16.7%
- 5 GPT-6 Luna 0%
Software & systems
5 models we track have a score here.
- 1 Claude Opus 5.5 97.0
- 2 Claude Sonnet 5.5 80.2
- 3 GPT-6.1 Sol ↑1 78.4
- 4 GPT-6 Astra ↓1 77.8
- 5 GPT-6 Luna 51.7
Enterprise operations
5 models we track have a score here.
- 1 GPT-6.1 Sol ↑3 73.0
- 2 GPT-6 Astra ↑1 65.0
- 3 Claude Opus 5.5 ↓2 54.9
- 4 Claude Sonnet 5.5 ↓2 52.5
- 5 GPT-6 Luna 34.4
Science
5 models we track have a score here.
- 1 Claude Opus 5.5 94.7
- 2 Claude Sonnet 5.5 84.3
- 3 GPT-6.1 Sol ↑1 82.4
- 4 GPT-6 Astra ↓1 82.2
- 5 GPT-6 Luna 66.9
Formal mathematics
5 models we track have a score here.
- 1 Claude Opus 5.5 97.7
- 2 GPT-6 Astra ↑1 97.2
- 3 GPT-6.1 Sol ↑1 95.4
- 4 Claude Sonnet 5.5 ↓2 90.4
- 5 GPT-6 Luna 36.5
Finance
5 models we track have a score here.
- 1 Claude Opus 5.5 87.8
- 2 GPT-6.1 Sol ↑2 85.0
- 3 GPT-6 Astra 84.0
- 4 Claude Sonnet 5.5 ↓2 70.7
- 5 GPT-6 Luna 68.5
Law
5 models we track have a score here.
- 1 Claude Opus 5.5 74.6
- 2 Claude Sonnet 5.5 73.8
- 3 GPT-6 Astra 73.6
- 4 GPT-6.1 Sol 72.7
- 5 GPT-6 Luna 66.2
Content design
5 models we track have a score here.
- 1 Claude Opus 5.5 83.1
- 2 GPT-6 Astra ↑1 81.9
- 3 Claude Sonnet 5.5 ↓1 81.8
- 4 GPT-6.1 Sol 81.7
- 5 GPT-6 Luna 76.2
3D production
5 models we track have a score here.
- 1 Claude Opus 5.5 71.8
- 2 Claude Sonnet 5.5 71.3
- 3 GPT-6 Astra 66.9
- 4 GPT-6.1 Sol 66.3
- 5 GPT-6 Luna 43.1
More effort adds a median 15 points
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The WorkflowArena paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 37% | ||
| Claude Opus 5.5 | high | Claude Code | 34.1% | $6.66 | |
| Claude Opus 5.5 | xhigh | Claude Code | 33.2% | ||
| Claude Sonnet 5.5 | max | Claude Code | 33.2% | ||
| GPT-6 Astra | xhigh | Codex | 30.8% | $29 | |
| GPT-6 Astra | high | Codex | 29.8% | ||
| GPT-6.1 Sol | xhigh | Codex | 29.5% | ||
| Claude Opus 5.5 | medium | Claude Code | 29.1% | ||
| GPT-6 Astra | medium | Codex | 28.1% | ||
| GPT-6.1 Sol | max | Codex | 28% | ||
| GPT-6 Astra | low | Codex | 27.8% | ||
| GPT-6.1 Sol | low | Codex | 27.6% | $3.61 | |
| GPT-6 Astra | max | Codex | 27.3% | ||
| GPT-6.1 Sol | medium | Codex | 27.3% | ||
| GPT-6.1 Sol | high | Codex | 25.6% | ||
| Claude Sonnet 5.5 | high | Claude Code | 25.3% | ||
| Claude Sonnet 5.5 | xhigh | Claude Code | 23.2% | ||
| Claude Opus 5.5 | low | Claude Code | 22% | ||
| Claude Sonnet 5.5 | medium | Claude Code | 19.8% | ||
| Claude Sonnet 5.5 | low | Claude Code | 16.9% | ||
| Claude Code + Kimi K3.1 Pro | max | Claude Code | 16.5% | ||
| GPT-6 Luna | max | Codex | 13.3% | ||
| Claude Code + Doubao Seed Evolving | high | Claude Code | 10.8% | ||
| Claude Code + DeepSeek V4.1 Flash | max | Claude Code | 6.08% | ||
| Claude Code + GLM-5.3-Flash | max | Claude Code | 4.43% |
More effort adds a median 15 points
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The WorkflowArena paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 37% | ||
| Claude Opus 5.5 | high | Claude Code | 34.1% | $6.66 | |
| Claude Opus 5.5 | xhigh | Claude Code | 33.2% | ||
| Claude Sonnet 5.5 | max | Claude Code | 33.2% | ||
| GPT-6 Astra | xhigh | Codex | 30.8% | $29 | |
| GPT-6 Astra | high | Codex | 29.8% | ||
| GPT-6.1 Sol | xhigh | Codex | 29.5% | ||
| Claude Opus 5.5 | medium | Claude Code | 29.1% | ||
| GPT-6 Astra | medium | Codex | 28.1% | ||
| GPT-6.1 Sol | max | Codex | 28% | ||
| GPT-6 Astra | low | Codex | 27.8% | ||
| GPT-6.1 Sol | low | Codex | 27.6% | $3.61 | |
| GPT-6 Astra | max | Codex | 27.3% | ||
| GPT-6.1 Sol | medium | Codex | 27.3% | ||
| GPT-6.1 Sol | high | Codex | 25.6% | ||
| Claude Sonnet 5.5 | high | Claude Code | 25.3% | ||
| Claude Sonnet 5.5 | xhigh | Claude Code | 23.2% | ||
| Claude Opus 5.5 | low | Claude Code | 22% | ||
| Claude Sonnet 5.5 | medium | Claude Code | 19.8% | ||
| Claude Sonnet 5.5 | low | Claude Code | 16.9% | ||
| GPT-6 Luna | max | Codex | 13.3% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The WorkflowArena paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official WorkflowArena 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 Games and long tasks
- ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
- Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games.
Gemini 2.5 Pro 3.90
- MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks.
Seed2.0 Pro 49%
- TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress.
Llama 4 Scout 7.00
- GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
- Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 5 models we track, plus 4 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 37%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on lab.einsia.ai: 25 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.