Atlas

Models

← All models

O3 (2025-04-16)

OpenAI · 2025-04-16

Immutable o3-2025-04-16 API snapshot evaluated by ReplicationBench.

Benchmark scores

BenchmarkScore
Arena Text — Business, Management & Financial Ops (No Style Control)1392
Arena Text — Chinese (No Style Control)1437
Arena Text — Creative Writing (No Style Control)1360
Arena Text — English (No Style Control)1415
Arena Text — Entertainment, Sports & Media (No Style Control)1374
Arena Text — Exclude Ties (No Style Control)1393
Arena Text — Exclude Ties (Style Controlled)1424
Arena Text — Expert (No Style Control)1400
Arena Text — French (No Style Control)1445
Arena Text — French (Style Controlled)1475
Arena Text — German (No Style Control)1419
Arena Text — Hard Prompts (No Style Control)1402
Arena Text — Hard Prompts English (No Style Control)1407
Arena Text — Instruction Following (No Style Control)1368
Arena Text — Japanese (No Style Control)1406
Arena Text — Korean (No Style Control)1370
Arena Text — Legal & Government (No Style Control)1429
Arena Text — Life, Physical & Social Science (No Style Control)1428
Arena Text — Longer Query (No Style Control)1371
Arena Text — Medicine & Healthcare (No Style Control)1448
Arena Text — Multi-turn (No Style Control)1405
Arena Text — Non-English (No Style Control)1404
Arena Text — Non-English (Style Controlled)1424
Arena Text — Occupational Mathematical (No Style Control)1422
Arena Text — Polish (No Style Control)1440
Arena Text — Polish (Style Controlled)1459
Arena Text — Russian (No Style Control)1408
Arena Text — Software & IT Services (No Style Control)1414
Arena Text — Spanish (No Style Control)1384
Arena Text — Writing, Literature & Language (No Style Control)1372
Loading Atlas data…