Model results

METR Time Horizons

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Use as a historical reference for task difficulty measured in human completion time.

Historical time horizon at 50% success, primarily software/ML/security tasks. Imported groups below may use different protocols; this review does not certify each run. Not actively updated after September 8, 2026. Results above 16 human-hours are unreliable for this suite.

Publisher results

← All evaluation groups

METR Time Horizons

Source: METR via Epoch AI
Version: Not reported
Measurement date: Not reported
Metric: min · Higher is better
Evaluation scope: 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.

Kimi K2 Thinking
moonshotai/kimi-k2-thinking-20251106
54.19 min
View modelEvidence aggregated
gpt-oss-120b
openai/gpt-oss-120b
41.98 min
View modelEvidence aggregated
Gemini 2.5 Pro Preview 06-05
google/gemini-2.5-pro-preview-06-05
38.73 min
View modelEvidence aggregated
R1 0528
deepseek/deepseek-r1-0528
31.17 min
View modelEvidence aggregated
R1
deepseek/deepseek-r1
26.93 min
View modelEvidence aggregated
DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
23.12 min
View modelEvidence aggregated
DeepSeek V3
deepseek/deepseek-chat-v3
18.47 min
View modelEvidence aggregated
GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13
9.17 min
View modelEvidence aggregated
Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
5.17 min
View modelEvidence aggregated