Model results
LiveBench
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.
Reviewed recommendation and limits
Use LiveBench V2 as a suite-level complement to AA Intelligence Index for a general-purpose shortlist. Start with its Browser Use or Agentic suite for screenshot interaction or persistent app work. Choose Reasoning for ground-truth answer checks.
V1 and V2 2026-10-14 stay separate. V2 equally averages measured suites and uses one run at supported effort. Grading mixes answer checks, tests, application outcomes and rubrics. Imported groups below may use different protocols; this review does not certify each run. Single runs and averages over different measured suites limit overall comparisons. Research uses rubrics and Design uses visual and structural grading; grader validation is not disclosed. V1 contamination claims do not certify V2. Measurement dates are not reported.
LiveBench overall
- Source
- LiveBench
- Version
- v1
- Measurement date
- 2024-08-31
- Metric
- % · Higher is better
- Evaluation scope
- Mean across that public release's task columns
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.
#1o1
openai/o1-2024-12-17
67.5%
View modelEvidence independent#2GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13
55.2%
View modelEvidence independent#3Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
53.9%
View modelEvidence independent#4Mistral Large 2407
mistralai/mistral-large-2407
49.9%
View modelEvidence independent