Model results

CursorBench

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

CursorBench

Source: Cursor via Epoch AI
Version: 4.0
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Reasoning level Medium · effort medium · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Gemini 4 Argon
google/gemini-4-argon-20261013
52.8%
View modelEvidence aggregated
Claude Opus 5.5
anthropic/claude-opus-5-5
52.5%
View modelEvidence aggregated
Claude Fable 5.1
anthropic/claude-fable-5-1
46.8%
View modelEvidence aggregated
Claude Opus 5
anthropic/claude-opus-5
43.3%
View modelEvidence aggregated
Grok 4.7
x-ai/grok-4.7-20260916
41.6%
View modelEvidence aggregated
Claude Sonnet 5.5
anthropic/claude-sonnet-5-5
39.2%
View modelEvidence aggregated
Gemini 3.8 Flash
google/gemini-3.8-flash-20260902
37.3%
View modelEvidence aggregated
Claude Haiku 5.5
anthropic/claude-haiku-5-5
36.9%
View modelEvidence aggregated
Grok 4.6
x-ai/grok-4.6-20260810
36.1%
View modelEvidence aggregated
Muse Spark 1.3
meta/muse-spark-1.3-20260902
32.6%
View modelEvidence aggregated
GPT-5.6 Sol
openai/gpt-5.6-sol-20260709
31.1%
View modelEvidence aggregated
Claude Sonnet 5
anthropic/claude-sonnet-5
28%
View modelEvidence aggregated
GPT-5.6 Terra
openai/gpt-5.6-terra-20260709
27.6%
View modelEvidence aggregated
GPT-5.6 Luna
openai/gpt-5.6-luna-20260709
22.2%
View modelEvidence aggregated