Atlas

Models

← All models

GPT-4.1 (2025-04-14)

OpenAI · 2025-04-14

Immutable GPT-4.1 API snapshot dated 2025-04-14 and evaluated on the Berkeley Function Calling Leaderboard v4.

Benchmark scores

BenchmarkScore
Arena Text — Business, Management & Financial Ops (No Style Control)1368
Arena Text — Chinese (No Style Control)1373
Arena Text — Creative Writing (No Style Control)1364
Arena Text — English (No Style Control)1390
Arena Text — Entertainment, Sports & Media (No Style Control)1364
Arena Text — Exclude Ties (No Style Control)1355
Arena Text — Exclude Ties (Style Controlled)1402
Arena Text — Expert (No Style Control)1363
Arena Text — French (No Style Control)1382
Arena Text — French (Style Controlled)1419
Arena Text — German (No Style Control)1381
Arena Text — Hard Prompts (No Style Control)1382
Arena Text — Hard Prompts English (No Style Control)1390
Arena Text — Instruction Following (No Style Control)1366
Arena Text — Japanese (No Style Control)1315
Arena Text — Korean (No Style Control)1349
Arena Text — Legal & Government (No Style Control)1399
Arena Text — Life, Physical & Social Science (No Style Control)1382
Arena Text — Longer Query (No Style Control)1383
Arena Text — Medicine & Healthcare (No Style Control)1379
Arena Text — Multi-turn (No Style Control)1397
Arena Text — Non-English (No Style Control)1370
Arena Text — Non-English (Style Controlled)1402
Arena Text — Occupational Mathematical (No Style Control)1358
Arena Text — Polish (No Style Control)1389
Arena Text — Polish (Style Controlled)1428
Arena Text — Russian (No Style Control)1373
Arena Text — Software & IT Services (No Style Control)1391
Arena Text — Spanish (No Style Control)1368
Arena Text — Writing, Literature & Language (No Style Control)1370
Loading Atlas data…