LLMs TigerLive LLM benchmarks

Gemini 3.7 Flash (high): benchmark scores, price and ranking

Gemini 3.7 Flash (high) from Google DeepMind ranks #29 of 741 LLMs on the LLMs Tiger aggregate benchmark score (53.9), based on 21 benchmark results captured up to 2026-10-05.

Organisation
Google DeepMind
Type
Fast / low-cost (flash) model
Open weights
No
Released
2026-08-13 (source: epoch)
Cheapest API price
$0.750 in / $3.75 out per million tokens (via aihubmix, observed 2026-10-05T21:47Z)
Aggregate rank
#29 of 741 (score 53.9)

Relative to other models, Gemini 3.7 Flash (high) is strongest on GPQA Diamond (#5 of 274) and weakest on Furniture Assembly (#21 of 25).

Gemini 3.7 Flash (high) benchmark results

Gemini 3.7 Flash (high) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
GPQA Diamond94.8%#5 of 274Epoch AI Benchmarking Hub2026-10-05
DTBench96.8%#6 of 149Epoch AI Benchmarking Hub2026-10-05
LMArena Vision Elo1,296#1 of 22LMArena2026-10-05
Chess Puzzles47.0%#11 of 124Epoch AI Benchmarking Hub2026-10-05
SimpleQA Verified69.2%#7 of 66Epoch AI Benchmarking Hub2026-10-05
OTIS Mock AIME97.2%#20 of 188Epoch AI Benchmarking Hub2026-10-05
SciCode56.8%#11 of 100Epoch AI Benchmarking Hub2026-10-05
ARC-AGI-284.6%#11 of 89ARC Prize official leaderboard2026-10-05
LMCA50.4%#14 of 111Epoch AI Benchmarking Hub2026-10-05
WebDev Arena1,587#11 of 63Epoch AI Benchmarking Hub2026-10-05
Mystery Games37.0%#14 of 57Epoch AI Benchmarking Hub2026-10-05
CritPt14.3%#30 of 111Epoch AI Benchmarking Hub2026-10-05
LMArena Text Elo1,488#8 of 28LMArena2026-10-05
FrontierMath T1-371.6%#20 of 69Epoch AI Benchmarking Hub2026-10-05
ALE-Bench904#27 of 78Epoch AI Benchmarking Hub2026-10-05
GDP.pdf23.8%#8 of 22Epoch AI Benchmarking Hub2026-10-05
FrontierMath T436.6%#22 of 52Epoch AI Benchmarking Hub2026-10-05
LMArena Code Elo1,592#18 of 29LMArena2026-10-05
DeepSWE65.3%#12 of 19Epoch AI Benchmarking Hub2026-10-05
FrontierSWE20.3%#12 of 16Epoch AI Benchmarking Hub2026-10-05
Furniture Assembly26.7%#21 of 25Epoch AI Benchmarking Hub2026-10-05

Gemini 3.7 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