Gemini 3.8 Flash
Google · 2026-09-02
Basic Information
- Developer
- Release Date
- 2026-09-02
- Overall Capability Index (ECI)
- 156.9
Benchmark Scores (Epoch AI)
Each benchmark also shows the model's rank among the models evaluated.
PhD-level science questions (GPQA Diamond) · #3 of 30
95.4%
Advanced mathematics (FrontierMath) · #25 of 30
68.4%
Expert-level questions across fields (HLE) · #4 of 30
44.5%
Factual question accuracy (SimpleQA Verified) · #7 of 30
69.7%
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#8 of 413 · 1495
- English#10 of 413 · 1498
- Math#5 of 396 · 1517
- Creative writing#7 of 411 · 1485
- Japanese#7 of 274 · 1503
- Image understanding (vision)#11 of 50 · 1290
- Agent task success#12 of 50 · 0.069
- Chinese#14 of 389 · 1536
- Korean#17 of 278 · 1456
- French#18 of 290 · 1506
- Spanish#19 of 295 · 1476
- Overall agent performance#21 of 50 · 0.03
- Coding#22 of 408 · 1530
- Web development#29 of 50 · 1583
- German#40 of 307 · 1472
Where to Use It
Models from Google are primarily available through Gemini. 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