Google · Benchmarks

Gemini 3.8 Flash benchmarks

Gemini 3.8 Flash has 5 published scores in this dataset, from a Google release dated 2026-09-02. Its composite index is 70.8, which places it 21st of 22 ranked models. Its strongest area is knowledge (index 97.6) and its weakest is coding (index 27.9). Its best placing is on GPQA Diamond, where its 95.3 ranks 2nd of 19 models with a published score.

Closed APIOfficial page

Category profile

Index 0–100: each score relative to the best published score on that test.

ReasoningCodingAgenticKnowledge
Reasoning
86.7#4 of 16 · 2 tests
Coding
27.91 test · not ranked
Agentic
—no data
Knowledge
97.61 test · not ranked

Model facts

Lab
Google
Type
Closed API
Released
2026-09-02
Context
1M
API price / 1M tokens
$0.75 in · $3.75 out

Gemini 3.8 Flash pricing and open alternatives

Gemini 3.8 Flash is only available through Google's API, so it cannot be self-hosted; it costs $0.75 per million input tokens and $3.75 per million output tokens.

Open-weight alternatives

The highest-ranked open models, which you can run on your own GPU.

Gemini 3.8 Flash speed and pricing

Measured figures link to their source; estimates are labelled.

API output speed
135 tok/sArtificial Analysis median · Artificial Analysis
Time to first token
2.91 sOpenRouter model page provider stats
API price per 1M tokens
$0.750 in · $3.75 outlab list price · Google Gemini API pricing
Compare speed and price across all models

Score by test

Rank is among every model with a published score on that test.

GPQA Diamond95.3%GPQA Diamond; competitor figure reported by OpenAI#2 of 19 · 0.8 behind GPT-6 AstraHumanity's Last Exam47.8%Humanity's Last Exam, no tools; AA independent run (High)#8 of 23 · 16.6 behind Claude Opus 5.5Terminal-Bench 4.019.7%Terminal-Bench 4.0; AA independent run (High)#16 of 16 · 50.9 behind Claude Sonnet 5.5MMMU-Pro85.6%MMMU-Pro (not original MMMU); AA independent run (High)#4 of 9 · 2.1 behind Claude Opus 5.5LMArena Text Elo1496LMArena Text, Overall; snapshot Oct 27, 2026; Gemini 3.8 Flash (High); +/-4#4 of 21 · 24 behind Gemini 4 Argon

Nearby in the composite ranking

Models with the closest composite index.

  1. 1Nemotron 3 Ultra74.4
  2. 2Gemma 4 26B A4B72.9
  3. 3Claude Haiku 5.572.4
  4. 4Gemini 3.8 Flash70.8
  5. 5gpt-oss-120b57.3

Head-to-head comparisons

Side-by-side pages built from the tests both models report.

Sources

ModelTestScoreSettingSource
Gemini 3.8 FlashGPQA Diamond95.3GPQA Diamond; competitor figure reported by OpenAIOpenAI GPT-6 Astra launch post (Academic table)
Gemini 3.8 FlashHumanity's Last Exam47.8Humanity's Last Exam, no tools; AA independent run (High)Artificial Analysis
Gemini 3.8 FlashTerminal-Bench 4.019.7Terminal-Bench 4.0; AA independent run (High)Artificial Analysis
Gemini 3.8 FlashMMMU-Pro85.6MMMU-Pro (not original MMMU); AA independent run (High)Artificial Analysis
Gemini 3.8 FlashLMArena Text Elo1496LMArena Text, Overall; snapshot Oct 27, 2026; Gemini 3.8 Flash (High); +/-4LMArena (arena.ai) Text leaderboard

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works