LLMs TigerLive LLM benchmarks

Gemini 3.8 Flash (high): benchmark scores, price and ranking

Gemini 3.8 Flash (high) from Google DeepMind ranks #37 of 741 LLMs on the LLMs Tiger aggregate benchmark score (53.5), based on 22 benchmark results captured up to 2026-10-05.

Organisation
Google DeepMind
Type
Fast / low-cost (flash) model
Open weights
No
Released
2026-09-02 (source: epoch)
Cheapest API price
$0.750 in / $3.75 out per million tokens (via gemini, observed 2026-10-05T21:47Z)
Aggregate rank
#37 of 741 (score 53.5)

Relative to other models, Gemini 3.8 Flash (high) is strongest on GPQA Diamond (#3 of 274) and weakest on FrontierSWE (#13 of 16).

Gemini 3.8 Flash (high) benchmark results

Gemini 3.8 Flash (high) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
GPQA Diamond95.4%#3 of 274Epoch AI Benchmarking Hub2026-10-05
Chess Puzzles61.0%#3 of 124Epoch AI Benchmarking Hub2026-10-05
DeepSWE73.8%#1 of 19Epoch AI Benchmarking Hub2026-10-05
OTIS Mock AIME98.9%#14 of 188Epoch AI Benchmarking Hub2026-10-05
SimpleQA Verified69.7%#5 of 66Epoch AI Benchmarking Hub2026-10-05
ARC-AGI-289.2%#9 of 89ARC Prize official leaderboard2026-10-05
LMArena Text Elo1,495#3 of 28LMArena2026-10-05
SciCode56.6%#12 of 100Epoch AI Benchmarking Hub2026-10-05
Surface Evolver76.9%#2 of 14Epoch AI Benchmarking Hub2026-10-05
ALE-Bench1,270#14 of 78Epoch AI Benchmarking Hub2026-10-05
Mystery Games47.0%#11 of 57Epoch AI Benchmarking Hub2026-10-05
CritPt18.3%#22 of 111Epoch AI Benchmarking Hub2026-10-05
WebDev Arena1,568#13 of 63Epoch AI Benchmarking Hub2026-10-05
LMArena Vision Elo1,290#5 of 22LMArena2026-10-05
FrontierMath T1-368.4%#23 of 69Epoch AI Benchmarking Hub2026-10-05
GDP.pdf23.2%#9 of 22Epoch AI Benchmarking Hub2026-10-05
WeirdML v37.4%#1 of 2Epoch AI Benchmarking Hub2026-10-05
FrontierMath T422.0%#35 of 52Epoch AI Benchmarking Hub2026-10-05
LMArena Code Elo1,583#20 of 29LMArena2026-10-05
Furniture Assembly31.7%#19 of 25Epoch AI Benchmarking Hub2026-10-05
CursorBench39.6%#10 of 13Epoch AI Benchmarking Hub2026-10-05
FrontierSWE19.6%#13 of 16Epoch AI Benchmarking Hub2026-10-05

Gemini 3.8 Flash (high) is also listed at 4 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

Compare it on the live leaderboard → · How the aggregate score works