Gemini 3.8 Flash

google/gemini-3.8-flash-20260902

Gemini 3.8 Flash is a model from Google. It accepts text, image, video, file, and audio inputs and generates text outputs. It supports a context length of 1,048,576 tokens, tools, and reasoning.

  • tool use
  • structured outputs
  • reasoning

At a glance

providergoogle
releasedSep 2, 2026
context1.0M
input / M$0.83

Specifications

What the API gives you

Context window
1.0M tokens
Max output
66K tokens
Input price
$0.83 / 1M tokens
Output price
$4.13 / 1M tokens
Cache read
$0.083 / 1M tokens
Modalities
text, image, video, file, audio → text
Knowledge cutoff
—
Released
Sep 2, 2026

Measured evidence

Public benchmark record

Design Arena Coding
1292 Elo2026-11-15
Design Arena UI
1303 Elo2026-11-15
Design Arena Web-app Agent
1213 Elo2026-11-15
Design Arena Website
1291 Elo2026-11-15
FACTS Grounding
68.2%2026-10-23evaluated 2026-10-23
FrontierMath Tiers 1-3 (Epoch AI)‡
68.4% ± 2.82026-09-02high effort, evaluated 2026-09-02
GPQA Diamond (Epoch AI)‡
95.4% ± 1.42026-09-02high effort, evaluated 2026-09-02
LiveBench Coding
72.5%2026-10-18
LiveBench Language
87.8%2026-10-18
LiveBench Math
91.6%2026-10-18
LiveBench Reasoning
89.3%2026-10-18
LMArena Agent‡
2.32026-11-11high effort
LMArena Agent Bash Recovery‡
-0.72026-10-08high effort
LMArena Agent Steerability‡
-1.32026-11-11high effort
LMArena Agent Task Outcome‡
1.32026-11-11high effort
LMArena Agent Tool Hallucination‡
0.42026-11-11high effort
LMArena Creative Writing‡
1493 Elo2026-11-11high effort
LMArena Instruction Following‡
1493 Elo2026-11-11high effort
LMArena Long Query‡
1508 Elo2026-11-11high effort
LMArena Math‡
1525 Elo2026-11-11high effort
LMArena Text‡
1497 Elo2026-11-11high effort
LMArena Text Factuality‡
1470 Elo2026-11-11high effort
LMArena Vision‡
1293 Elo2026-11-09high effort
LMArena Vision Diagrams‡
1342 Elo2026-11-09high effort
LMArena Vision OCR‡
1315 Elo2026-11-09high effort
LMArena WebDev‡
1583 Elo2026-11-11high effort
LMArena WebDev Image-to-Web‡
1594 Elo2026-11-10high effort
OTIS Mock AIME (Epoch AI)‡
98.9% ± 0.92026-09-02high effort, evaluated 2026-09-02
SimpleQA Verified (Epoch AI)‡
69.7% ± 1.52026-09-02high effort, evaluated 2026-09-02
Terminal-Bench (4.1)‡
18.2%2026-11-15mini-SWE-agent, high effort, evaluated 2026-11-03

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Competition MathEstablished evidence

    100% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Business WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

Show all 45 tasks
  • Best LLM for Frontend & UIEstablished evidence

    100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    100% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • 85% of intended weighted task evidence across 3 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    85% of intended weighted task evidence across 3 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingEstablished evidence

    80% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionEstablished evidence

    79% of intended weighted task evidence across 2 independent sources. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsEstablished evidence

    67% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    64% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • 64% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGEstablished evidence

    62% of intended weighted task evidence across 3 independent sources. 5 of 7 configured evaluation feeds currently have results.

  • 61% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • 61% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best Value LLMEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsEstablished evidence

    50% of intended weighted task evidence across 3 independent sources. 9 of 9 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best Local LLM for CodingEstablished evidence

    47% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • 35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • 60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    58% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • 38% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 6 of 7 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.

  • 21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 1 of 3 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

Official release evidence · provisional

What the launch material actually says

Verbatim claims from the model provider. These help on launch day but do not count as independent confirmation.

Recommendation coverage

Where this model appears

  1. #1Best LLM for Vision & Documents
  2. #1Best LLM for Translation
  3. #1Best LLM for Literary Translation
  4. #1Best LLM for Document Parsing
  5. #1Best LLM for Fast Summaries
  6. #1Best LLM for OCR & Documents
  7. #1Best LLM for Roleplay & Character
  8. #1Best LLM for Creative Writing
  9. #1Best LLM for Writing
  10. #1Best LLM for Business Writing
  11. #1Best LLM for Marketing Copy
  12. #1Best LLM for Everyday Translation
  13. #1Best LLM for Charts & Diagrams
  14. #1Best LLM for Chat & Roleplay
  15. #3Best Value LLM
  16. #3Best LLM for Logic & Problem Solving
  17. #3Best LLM for a General Assistant
  18. #4Best LLM for Image Understanding
  19. #5Best LLM for Document Summarization
  20. #5Best LLM for Summarization
  21. #5Best LLM for Massive Context
  22. #6Best LLM for RAG & Long Context
  23. #7Cheapest Capable LLM
  24. #7Best Cheap LLM for High Volume
  25. #8Best LLM for Grounded RAG

Compare head to head

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.