Skip to content

Benchmark

AppWorld Test-Normal 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

26.9%
Mean
14.3%
Median
30.1%
Std dev
0%
10th percentile
76.2%
90th percentile
0%
Min
0%90.5%
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 docs90.5%
claude-opus-4-7LARA MAS (23715209-d5c9ade3)· AppWorld Leaderboard data docs71.4%
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 docs76.2%
GLM-5.3-FlashIBM CUGA (a2db3f1e-2c28b1b2)· AppWorld Leaderboard data docs81%
GPT-4 TurboFullCodeRefl (571aa685-a8671c57)· AppWorld Leaderboard data docs0%
GPT-4 TurboIPFunCall (08d2ff3e-a0589430)· AppWorld Leaderboard data docs14.3%
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 docs38.1%
gpt-4.1-miniLARA MAS (695a4b55-1b68dde4)· AppWorld Leaderboard data docs28.6%
GPT-4oFullCodeRefl (d035381e-2d30c0e3)· AppWorld Leaderboard data docs4.8%
GPT-4oIPFunCall (3a889687-923696fe)· AppWorld Leaderboard data docs9.5%
GPT-4oPlanExec (ac5b742b-aa0243da)· AppWorld Leaderboard data docs4.8%
GPT-4oReAct (3414a75f-3df6a61f)· AppWorld Leaderboard data docs9.5%
GPT-4oReAct + 2 SetBSR Demos (1c12639a-57a0ac34)· AppWorld Leaderboard data docs33.3%
gpt-5.6-lunakecaipan capybara (1095b768-6513e0c6)· AppWorld Leaderboard data docs57.1%
gptoss-20bRooAGI_agentbuilder_memtune_rl (5acab4bb-badb978f)· AppWorld Leaderboard data docs33.3%
LLaMA3-70BFullCodeRefl (baf95530-cee120fc)· AppWorld Leaderboard data docs0%
LLaMA3-70BPlanExec (77f25849-862250c4)· AppWorld Leaderboard data docs0%
LLaMA3-70BReAct (4077db41-07bc5204)· AppWorld Leaderboard data docs4.8%
Qwen2.5-32BLOOP (e5e08b7e-d8e6474f)· AppWorld Leaderboard data docs14.3%
Qwen3-14BAlibaba Cloud ApsaraLab AgentRL (cabab065-0caee3c3)· AppWorld Leaderboard data docs57.1%
Qwen3.5-27BSynthAPI (3bd98253-d4fa6c8e)· AppWorld Leaderboard data docs71.4%

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