Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check

Back to leaderboard

OpenAI · Active

GPT-5.6 Terra

gpt-terra family · launched 2026-07-09

MultimodalReasoningToolsStructured

AITopic score69.9#27 overall

Balanced GPT-5.6 model for capable, cost-efficient everyday work

Evidence coverage100%9 evaluations · 3 institutions

Context / maximum output1M / 128ktokens

Cache / input / output$0.2 · $1.5 · $9USD per million tokens

Value / freshness56.2 / 75relative value · release freshness

Product profile

What this model supports

Inputtext, image, pdf

Outputtext

Knowledge cutoff2026-02-16

WeightsProprietary / hosted

Capability profile

Strengths by domain

Coding73.12 public results

Research & reasoning78.12 public results

Professional work63.92 public results

Knowledge & instruction60.42 public results

Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding2 results

LiveBench 2.0 · CodingLiveBench86.20 scoreReading 86.2

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · CodingAIHOT60.00 scoreReading 60.0

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench90.60 scoreReading 90.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · ResearchAIHOT65.60 scoreReading 65.6

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Professional work2 results

LiveBench 2.0 · ProfessionalLiveBench64.68 scoreReading 64.7

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AIHOT · ProfessionalAIHOT63.10 scoreReading 63.1

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Knowledge & instruction2 results

AIHOT · KnowledgeAIHOT60.70 scoreReading 60.7

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

LiveBench 2.0 · KnowledgeLiveBench60.40 scoreReading 60.4

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Human preference & indices4 results

LiveBenchLiveBench70.84 scoreReading 70.8

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Arena TextLMArena1,448.3 EloReading 69.9

Direct LMArena text leaderboard result.

AIHOT aggregate leaderboardAIHOT61.60 scoreReading 61.6

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

AA IndexArtificial Analysis64.55 indexReading 57.0

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence