Model results

ReactBench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

ReactBench

Source: ReactBench (reviewed publisher results)
Version: 1.1
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Overall pass@1 across tasks; effort=High; result date not supplied; source captured 2026-09-10

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1Claude Opus 5
anthropic/claude-opus-5
42.1%
View modelEvidence independent
#2Claude Fable 5.1
anthropic/claude-fable-5-1
40.5%
View modelEvidence independent
#3Claude Fable 5
anthropic/claude-fable-5
39%
View modelEvidence independent
#4GPT-5.6 Sol
openai/gpt-5.6-sol-20260709
37.4%
View modelEvidence independent
#5GPT-5.6 Terra
openai/gpt-5.6-terra-20260709
36.9%
View modelEvidence independent
#6GPT-5.6 Luna
openai/gpt-5.6-luna-20260709
30.8%
View modelEvidence independent
#6Grok 4.6
x-ai/grok-4.6-20260810
30.8%
View modelEvidence independent
#8Claude Sonnet 5
anthropic/claude-sonnet-5
28.2%
View modelEvidence independent
#9Claude Opus 4.8
anthropic/claude-opus-4-8
25.6%
View modelEvidence independent