Benchmark
AppWorld Test-Challenge: Task Goal Completion
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models and systems measured
- 26
- Scores recorded
- 26
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 35.6%
- Mean
- 19.7%
- Median
- 30.8%
- Std dev
- 3.4%
- 10th percentile
- 85.6%
- 90th percentile
- 0.7%
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Claude Opus 4.6Button Agent (f072cd07-6ae0fbdf)· AppWorld Leaderboard data docs | 72.4% |
| claude-opus-4-7LARA MAS (23715209-d5c9ade3)· AppWorld Leaderboard data docs | 85.6% |
| DeepSeekCoderFullCodeRefl (0465049f-bff9fca2)· AppWorld Leaderboard data docs | 5.8% |
| DeepSeekCoderPlanExec (871bf9fd-4de66f57)· AppWorld Leaderboard data docs | 0.7% |
| DeepSeekCoderReAct (9ae299b8-25c255f5)· AppWorld Leaderboard data docs | 2.9% |
| GLM-5.3AtlasHarness (65df675b-ca5e4771)· AppWorld Leaderboard data docs | 89.5% |
| GLM-5.3-FlashIBM CUGA (a2db3f1e-2c28b1b2)· AppWorld Leaderboard data docs | 92.8% |
| GPT-4 TurboFullCodeRefl (571aa685-a8671c57)· AppWorld Leaderboard data docs | 12.5% |
| GPT-4 TurboIPFunCall (08d2ff3e-a0589430)· AppWorld Leaderboard data docs | 14.6% |
| GPT-4 TurboPlanExec (c722a232-74b9384b)· AppWorld Leaderboard data docs | 11% |
| GPT-4 TurboReAct (1f0055c0-123849bb)· AppWorld Leaderboard data docs | 17.5% |
| GPT-4.1IBM CUGA (8a02d49a-0df800d6)· AppWorld Leaderboard data docs | 57.6% |
| gpt-4.1-miniLARA MAS (695a4b55-1b68dde4)· AppWorld Leaderboard data docs | 37.6% |
| GPT-4oFullCodeRefl (d035381e-2d30c0e3)· AppWorld Leaderboard data docs | 19.2% |
| GPT-4oIPFunCall (3a889687-923696fe)· AppWorld Leaderboard data docs | 18% |
| GPT-4oPlanExec (ac5b742b-aa0243da)· AppWorld Leaderboard data docs | 19.7% |
| GPT-4oReAct (3414a75f-3df6a61f)· AppWorld Leaderboard data docs | 30.2% |
| GPT-4oReAct + 2 SetBSR Demos (1c12639a-57a0ac34)· AppWorld Leaderboard data docs | 38.9% |
| gpt-5.6-lunakecaipan capybara (1095b768-6513e0c6)· AppWorld Leaderboard data docs | 73.4% |
| gptoss-20bRooAGI_agentbuilder_memtune_rl (5acab4bb-badb978f)· AppWorld Leaderboard data docs | 15.3% |
| LLaMA3-70BFullCodeRefl (baf95530-cee120fc)· AppWorld Leaderboard data docs | 7% |
| LLaMA3-70BPlanExec (77f25849-862250c4)· AppWorld Leaderboard data docs | 2.4% |
| LLaMA3-70BReAct (4077db41-07bc5204)· AppWorld Leaderboard data docs | 3.4% |
| Qwen2.5-32BLOOP (e5e08b7e-d8e6474f)· AppWorld Leaderboard data docs | 47.2% |
| Qwen3-14BAlibaba Cloud ApsaraLab AgentRL (cabab065-0caee3c3)· AppWorld Leaderboard data docs | 67.6% |
| Qwen3.5-27BSynthAPI (3bd98253-d4fa6c8e)· AppWorld Leaderboard data docs | 83.7% |