GPT-5.6 Luna
OpenAI · 2026-07-09
Basic Information
- Developer
- OOpenAI
- Release Date
- 2026-07-09
- Overall Capability Index (ECI)
- 156.5
Benchmark Scores (Epoch AI)
Each benchmark also shows the model's rank among the models evaluated.
OPhD-level science questions (GPQA Diamond) · #26 of 30
91.6%
OAdvanced mathematics (FrontierMath) · #14 of 30
82.1%
OReasoning through unfamiliar puzzles (ARC-AGI-2) · #27 of 30
59.5%
Bars show accuracy (%) and start at 0%.
User Vote Rankings (LMArena)
Rankings based on people's votes comparing responses from two models. Models do not appear on leaderboards where they have too few votes.
- Overall#75 of 413 · 1453
- English#66 of 413 · 1467
- Document understanding#23 of 44 · 1457
- German#32 of 307 · 1476
- Overall agent performance#35 of 50 · -0.012
- Agent task success#35 of 50 · -0.033
- Math#39 of 396 · 1477
- Image understanding (vision)#44 of 50 · 1260
- Spanish#46 of 295 · 1463
- Web development#47 of 50 · 1518
- French#50 of 290 · 1482
- Japanese#54 of 274 · 1430
- Korean#63 of 278 · 1414
- Coding#74 of 408 · 1501
- Creative writing#93 of 411 · 1409
- Chinese#100 of 389 · 1476
Where to Use It
Models from OpenAI are primarily available through ChatGPT. Available models and usage limits vary by plan, so check the pricing and free access page.
Scores and rankings are reproduced directly from public sources and were not measured by this site. Model names vary slightly across sources and are matched automatically, so different versions may occasionally be mixed together.
Source: Epoch AI (CC BY 4.0) · Checked 2026-10-04 · LMArena (CC BY 4.0) · Checked 2026-10-04