BenchLeader

Claude Sonnet 5 vs Gemini 3.8 Flash

Verdict
  • Gemini 3.8 Flash (medium) leads on quality: 63.6 vs 61.4.
  • Claude Sonnet 5 (high) is stronger in agents & tools, human preference, reasoning.
  • Gemini 3.8 Flash (medium) is stronger in coding, composite, knowledge, long context, multimodal.
  • Gemini 3.8 Flash (medium) is 2.7× cheaper ($1.50 vs $4.00 per 1M blended).
  • Gemini 3.8 Flash (medium) streams 1.5× faster (90 vs 60 tokens per second).
MetricClaude Sonnet 5 (high)Gemini 3.8 Flash (medium)
BenchLeader Index61.463.6
Agents & tools score61.8
Coding score61.663.8
Composite score69.579.6
Human preference score66.2
Knowledge score62.477.7
Long context score64.868.6
Multimodal score63.168.8
Reasoning score66.8
Blended price $/M$4.00$1.50
Output speed60 tok/s90 tok/s
Time to first answer10.0 s11.7 s
Context window1M1M
SciCode48.6%54.4%
WeirdML68.8%
LMArena Text1462
LMArena Hard Prompts1490
LMArena Coding1521
LMArena WebDev1538
LMArena Vision1278
LMArena Agent6.3
AA Intelligence Index32.040
AA-LCR76.7%84.0%
MMMU-Pro84.2%
AA-Omniscience-3.728.6
GPQA Diamond (AA)93.5%
Humanity's Last Exam (AA)35.7%42.1%
SciCode (AA)54.3%55.1%

Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.

Claude Sonnet 5 vs Gemini 3.8 Flash: questions

Is Claude Sonnet 5 better than Gemini 3.8 Flash?
Gemini 3.8 Flash (medium) leads on quality: 63.6 vs 61.4. The BenchLeader Index combines every independent quality benchmark; Gemini 3.8 Flash (medium) is ahead overall as of 2026-09-10, but check the category scores for your use.
Is Claude Sonnet 5 better than Gemini 3.8 Flash for coding?
Gemini 3.8 Flash scores higher in coding (64 vs 62 on the category index, where 50 is average).
Which is cheaper, Claude Sonnet 5 or Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper: $1.50 against $4.00 per million tokens, blended at three input tokens per output token.
Which is faster, Claude Sonnet 5 or Gemini 3.8 Flash?
Gemini 3.8 Flash streams faster: 90 against 60 output tokens per second.
Which has the larger context window?
Both accept 1M tokens of context.