GPT-5.6 Terra — benchmark results

OpenAI's balanced GPT-5.6 tier for everyday reasoning and coding work. Provider: OpenAI. Released 2026-07-09. Access: API.

Unified ELO 1879 ± 16, rank #79 of 1776 rated models, from 104 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
WolfBench82Average Score (%)96.8
Vals AI TaxEval v276.17Accuracy (%)96.5
ZeroEval GPQA Diamond92.9GPQA Diamond Score96
LLM Stats (MRCR v2 (8-needle))89.6Score (%)95
BenchLM72.6Overall Score94.9
LLM Stats (BrowseComp)87.5Score (%)94.6
Gert Labs Rankings67.02GScore (%)94.2
Benchmarks.bio - SpatialBench-Long22.22Pass Rate (%)94.1
Vals AI ProofBench71Accuracy (%)93.8
Epoch AI - ECI158.36ECI Score93.4
RuneBench5934Total Peak XP Rate (XP/min)92.1
EQ-Bench Longform Writing78Writing Score (0-100)91.8

Interactive version: theaggregate.ai/model?slug=gpt-5-6-terra · How the rankings work · Data refreshed daily, snapshot 2026-07-22.