Skip to content

Benchmark

AppWorld Test-Challenge Level 3: Scenario 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

22.9%
Mean
4.6%
Median
29.9%
Std dev
0%
10th percentile
75.4%
90th percentile
0%
Min
0%87.7%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Claude Opus 4.6Button Agent (f072cd07-6ae0fbdf)· AppWorld Leaderboard data docs64.6%
claude-opus-4-7LARA MAS (23715209-d5c9ade3)· AppWorld Leaderboard data docs75.4%
DeepSeekCoderFullCodeRefl (0465049f-bff9fca2)· AppWorld Leaderboard data docs0%
DeepSeekCoderPlanExec (871bf9fd-4de66f57)· AppWorld Leaderboard data docs0%
DeepSeekCoderReAct (9ae299b8-25c255f5)· AppWorld Leaderboard data docs0%
GLM-5.3AtlasHarness (65df675b-ca5e4771)· AppWorld Leaderboard data docs80%
GLM-5.3-FlashIBM CUGA (a2db3f1e-2c28b1b2)· AppWorld Leaderboard data docs87.7%
GPT-4 TurboFullCodeRefl (571aa685-a8671c57)· AppWorld Leaderboard data docs0%
GPT-4 TurboIPFunCall (08d2ff3e-a0589430)· AppWorld Leaderboard data docs3.1%
GPT-4 TurboPlanExec (c722a232-74b9384b)· AppWorld Leaderboard data docs0%
GPT-4 TurboReAct (1f0055c0-123849bb)· AppWorld Leaderboard data docs0%
GPT-4.1IBM CUGA (8a02d49a-0df800d6)· AppWorld Leaderboard data docs38.5%
gpt-4.1-miniLARA MAS (695a4b55-1b68dde4)· AppWorld Leaderboard data docs12.3%
GPT-4oFullCodeRefl (d035381e-2d30c0e3)· AppWorld Leaderboard data docs3.1%
GPT-4oIPFunCall (3a889687-923696fe)· AppWorld Leaderboard data docs4.6%
GPT-4oPlanExec (ac5b742b-aa0243da)· AppWorld Leaderboard data docs1.5%
GPT-4oReAct (3414a75f-3df6a61f)· AppWorld Leaderboard data docs6.2%
GPT-4oReAct + 2 SetBSR Demos (1c12639a-57a0ac34)· AppWorld Leaderboard data docs18.5%
gpt-5.6-lunakecaipan capybara (1095b768-6513e0c6)· AppWorld Leaderboard data docs53.8%
gptoss-20bRooAGI_agentbuilder_memtune_rl (5acab4bb-badb978f)· AppWorld Leaderboard data docs1.5%
LLaMA3-70BFullCodeRefl (baf95530-cee120fc)· AppWorld Leaderboard data docs1.5%
LLaMA3-70BPlanExec (77f25849-862250c4)· AppWorld Leaderboard data docs0%
LLaMA3-70BReAct (4077db41-07bc5204)· AppWorld Leaderboard data docs0%
Qwen2.5-32BLOOP (e5e08b7e-d8e6474f)· AppWorld Leaderboard data docs23.1%
Qwen3-14BAlibaba Cloud ApsaraLab AgentRL (cabab065-0caee3c3)· AppWorld Leaderboard data docs47.7%
Qwen3.5-27BSynthAPI (3bd98253-d4fa6c8e)· AppWorld Leaderboard data docs72.3%

Data credits: AppWorld leaderboard (Stony Brook NLP). Aggregate scores from the official leaderboard; no results licence asserted. Protected bundles and experiment outputs are not used