ObviousBench

PUBLIC MODEL RELIABILITY · LAB VIEW

OpenAI

92 public configurations across 32 model families in the 2026-07-25 release. The global cost frontier stays available as context.

Open OpenAI on the cost frontier Compare the full public field

GLOBAL REFERENCE RETAINED

Where OpenAI sits in the complete public field

The lab is highlighted without changing the frontier calculation or zoom. This preserves the comparison frame that a provider-only chart would otherwise hide.

OpenAI in the global fieldAll 432 public configurations on the same global log-cost and pass3 scale as the homepage frontier. Public field OpenAIGlobal Pareto
OpenAI configurations highlighted in the global ObviousBench cost and reliability field 100% 95% 90% 80% 60% 40% 20% 10% More expensive Cheaper

This is a fixed global reference, not a recomputed OpenAI frontier.

CURATED DETAIL

Decision pages for OpenAI

These highlighted cards have an indexable evidence page. The rest remain in the full explorer rather than being turned into thin pages.

GPT 5.5Best observed 100% · $0.744 GPT 5.6 TerraBest observed 96.5% · $0.2614

FULL LAB VIEW

All observed OpenAI model families

Sorted by highest observed answer pass3, then the lowest cost at that score. Release dates are not inferred because this release data does not encode a consistent vendor release-date field.

o3Best observed 100% · $0.5356
GPT 5Best observed 100% · $0.7079
GPT 5.5Best observed 100% · $0.744
o4 miniBest observed 98.6% · $0.4127
GPT 5.4Best observed 98.6% · $0.6939
GPT 5.2Best observed 98.6% · $0.8128
o1Best observed 98.6% · $11.42
o3 mini HighBest observed 97.9% · $1.917
GPT 5 nanoBest observed 97.2% · $0.1104
o4 mini HighBest observed 97.2% · $0.4149
o3 miniBest observed 97.2% · $1.869
GPT 5.6 TerraBest observed 96.5% · $0.2614
GPT 5 miniBest observed 95.8% · $0.2528
GPT OSS 120BBest observed 94.4% · $0.008422
GPT 5.6 LunaBest observed 93.8% · $0.1165
GPT 5.4 miniBest observed 93.8% · $0.2757
GPT 5.6 SolBest observed 93.8% · $0.2961
GPT OSS 20BBest observed 92.4% · $0.01742
GPT 5.4 nanoBest observed 91.7% · $0.0809
GPT 4o 2024 11 20Best observed 77.1% · $0.06045
GPT 4.1Best observed 75.7% · $0.04971
GPT 4o 2024 08 06Best observed 75% · $0.06312
GPT 4Best observed 72.9% · $0.682
GPT 4o 2024 05 13Best observed 70.8% · $0.1202
GPT 4 TurboBest observed 70.1% · $0.2329
GPT 4.1 miniBest observed 64.6% · $0.009498
GPT 3.5 Turbo 0613Best observed 63.9% · $0.02264
GPT 4o mini 2024 07 18Best observed 59% · $0.003663
GPT 4.1 nanoBest observed 52.1% · $0.002382
GPT 3.5 Turbo 16kBest observed 50.7% · $0.06468
GPT 3.5 TurboBest observed 45.1% · $0.01175
GPT 3.5 Turbo InstructBest observed 17.4% · $0.03707