GPT-6.1 Terra
OpenAI·Released Oct 26, 2026
Updated Oct 28, 6:21 AM ET
The score is on the board's scale (reference average 50, about 15 points per standard deviation), not a percentage.
By domain
Each domain is scored on the same scale as the overall score. Coverage is the share of the domain's kinds of evaluation with a result; it says how much evidence there is, not how good the model is.
Every result behind the score
The result as the evaluator publishes it, and the reading it gives on the board's scale. A hard evaluation can give a high reading for a modest result; results near 95% or 5% only say "at least" or "at most".
Coding
4 results · 64.0- Terminal-Bench 4.0Vals AI · max effort49.5%Reading 74.6
- Terminal-Bench 4.0 (AA run)Artificial Analysis · high effort41.9%Reading 72.4
- Vibe Code BenchVals AI · max effort84.0%Reading 66.7
- SciCodeArtificial Analysis · high effort51.6%Reading 52.9
Research and reasoning
4 results · 78.3- Mystery Game PuzzlesEpoch AI · max effort74.0%Reading 94.6
- FrontierMath Tier 4Epoch AI · max effort92.7%Reading 94.3
- FrontierMath Tiers 1–3Epoch AI · max effort90.9%Reading 82.8
- Humanity's Last Exam (AA run)Artificial Analysis · high effort43.3%Reading 60.1
Professional work
4 results · 47.1- APEX-AgentsMercor · max effort68.3%Reading 77.0
- Legal Research BenchVals AI · max effort26.0%Reading 43.3
- Tax Agent BenchVals AI · max effort15.2%Reading 35.8
- Harvey Legal Agent BenchmarkVals AI · max effortCappedNear the floor1.7%Reading at most 11.2
Knowledge and accuracy
2 results · 59.9- SimpleQA VerifiedEpoch AI · max effort57.3%Reading 65.6
- AA-LCRArtificial Analysis · high effort82.3%Reading 53.4
Shown, not scored
Composite indices, saturated or older evaluations, evaluations still being checked, and vision, writing and multilingual results. They do not move the score.
- OTIS Mock AIMEEpoch AI · Research and reasoningReference only100.0%
- EBR-benchEpoch AI · Professional workWatching78.1%
- GPQA DiamondEpoch AI · Knowledge and accuracyReference only94.3%
- AA Intelligence IndexArtificial Analysis · Composite indicesReference only42.3
- Vals IndexVals AI · Composite indicesReference only60.2%
- Arena WebDevLMArena · Writing and designReference only1,670.7
No result yet
Scored evaluations this model has not taken. A missing result neither adds nor subtracts.
- LiveBench Coding · LiveBench
- Code Migration · Vals AI
- ProgramBench · Vals AI
- Vibe Code Bench 1–100 · Vals AI
- CyberBench Patch · Vals AI
- APEX-SWE · Mercor
- LiveBench Reasoning · LiveBench
- Chess Puzzles · Epoch AI
- MysteryMechanism · Vals AI
- Terminal-Bench Science · Vals AI
- ProofBench · Vals AI
- Finance Agent · Vals AI
- MedCode · Vals AI
- EMB · Vals AI
- LiveBench Data Analysis · LiveBench
- τ²-Bench Telecom (AA run) · Artificial Analysis
- τ-Bench Banking (AA run) · Artificial Analysis
- LiveBench Language · LiveBench
- LiveBench Instruction Following · LiveBench
- BullshitBench · BullshitBench
- IFBench (AA run) · Artificial Analysis
- Arena Text · LMArena