Skip to content

Benchmark

AppWorld Test-Challenge Level 1: 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

41.5%
Mean
37.5%
Median
29.9%
Std dev
4.2%
10th percentile
83.3%
90th percentile
0%
Min
0%91.7%
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 docs70.8%
claude-opus-4-7LARA MAS (23715209-d5c9ade3)· AppWorld Leaderboard data docs83.3%
DeepSeekCoderFullCodeRefl (0465049f-bff9fca2)· AppWorld Leaderboard data docs12.5%
DeepSeekCoderPlanExec (871bf9fd-4de66f57)· AppWorld Leaderboard data docs0%
DeepSeekCoderReAct (9ae299b8-25c255f5)· AppWorld Leaderboard data docs4.2%
GLM-5.3AtlasHarness (65df675b-ca5e4771)· AppWorld Leaderboard data docs83.3%
GLM-5.3-FlashIBM CUGA (a2db3f1e-2c28b1b2)· AppWorld Leaderboard data docs83.3%
GPT-4 TurboFullCodeRefl (571aa685-a8671c57)· AppWorld Leaderboard data docs33.3%
GPT-4 TurboIPFunCall (08d2ff3e-a0589430)· AppWorld Leaderboard data docs16.7%
GPT-4 TurboPlanExec (c722a232-74b9384b)· AppWorld Leaderboard data docs16.7%
GPT-4 TurboReAct (1f0055c0-123849bb)· AppWorld Leaderboard data docs20.8%
GPT-4.1IBM CUGA (8a02d49a-0df800d6)· AppWorld Leaderboard data docs87.5%
gpt-4.1-miniLARA MAS (695a4b55-1b68dde4)· AppWorld Leaderboard data docs45.8%
GPT-4oFullCodeRefl (d035381e-2d30c0e3)· AppWorld Leaderboard data docs41.7%
GPT-4oIPFunCall (3a889687-923696fe)· AppWorld Leaderboard data docs12.5%
GPT-4oPlanExec (ac5b742b-aa0243da)· AppWorld Leaderboard data docs29.2%
GPT-4oReAct (3414a75f-3df6a61f)· AppWorld Leaderboard data docs33.3%
GPT-4oReAct + 2 SetBSR Demos (1c12639a-57a0ac34)· AppWorld Leaderboard data docs54.2%
gpt-5.6-lunakecaipan capybara (1095b768-6513e0c6)· AppWorld Leaderboard data docs58.3%
gptoss-20bRooAGI_agentbuilder_memtune_rl (5acab4bb-badb978f)· AppWorld Leaderboard data docs37.5%
LLaMA3-70BFullCodeRefl (baf95530-cee120fc)· AppWorld Leaderboard data docs20.8%
LLaMA3-70BPlanExec (77f25849-862250c4)· AppWorld Leaderboard data docs4.2%
LLaMA3-70BReAct (4077db41-07bc5204)· AppWorld Leaderboard data docs0%
Qwen2.5-32BLOOP (e5e08b7e-d8e6474f)· AppWorld Leaderboard data docs58.3%
Qwen3-14BAlibaba Cloud ApsaraLab AgentRL (cabab065-0caee3c3)· AppWorld Leaderboard data docs79.2%
Qwen3.5-27BSynthAPI (3bd98253-d4fa6c8e)· AppWorld Leaderboard data docs91.7%

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