Claude Sonnet 5 vs Gemini 3.8 Flash: Specs & Benchmark Comparison

Claude Sonnet 5 is developed by Anthropic, while Gemini 3.8 Flash comes from Google. Claude Sonnet 5 was released in June 2026, and Gemini 3.8 Flash followed 3 months later in September 2026.

The two models share 4 published benchmarks. They split them evenly, 2 to 2. The widest gaps are on GDP.pdf, where Claude Sonnet 5 scores 81.6% against 35.0%; DeepSWE 1.1, where Gemini 3.8 Flash scores 73.7% against 54.0%. Averaged across everything we track, Claude Sonnet 5 sits at 58.4% and Gemini 3.8 Flash at 59.2%.

Gemini 3.8 Flash is the cheaper API at $0.75 per million input tokens and $3.75 per million output tokens, roughly 3 times cheaper than Claude Sonnet 5 at $2 and $10. Both accept a context window of about 1M tokens. Claude Sonnet 5 accepts text and images as input, while Gemini 3.8 Flash accepts text, images, audio, and video.

CharacteristicClaude Sonnet 5Gemini 3.8 Flash
CompanyAnthropicGoogle
Release DateJune 30, 2026September 2, 2026
Parameters——
MultimodalYesYes
Context (input)1.0M1.0M
Context (output)64K66K
Input Price / 1M$2.00$0.75
Output Price / 1M$10.00$3.75
Average Score58.4%59.2%
Benchmarks
GDP.pdf81.6%35.0%
DeepSWE 1.154.0%73.7%
Terminal-Bench 4.012.4%19.1%
CharXiv-R88.3%86.2%

Visual Benchmark Comparison

Claude Sonnet 5
Gemini 3.8 Flash
GDP.pdf0.8 vs 0.3
0.8
0.3
DeepSWE 1.10.5 vs 0.7
0.5
0.7
Terminal-Bench 4.00.1 vs 0.2
0.1
0.2
CharXiv-R0.9 vs 0.9
0.9
0.9

Verdict

Gemini 3.8 Flash leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Claude Sonnet 5 — 0.6, Gemini 3.8 Flash — 0.6.

API Cost

Gemini 3.8 Flash is 2.7x cheaper: input $0.75/1M vs $2.00/1M tokens.

Context Window

Same context size: 1M tokens.

Recency

Gemini 3.8 Flash is newer: released 9/2/2026 vs 6/30/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Claude Sonnet 5 or Gemini 3.8 Flash?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Claude Sonnet 5 or Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper for input: $0.75 per 1M tokens vs $2.00.
Which has a larger context window — Claude Sonnet 5 or Gemini 3.8 Flash?
Claude Sonnet 5 supports a larger context: 1,048,576 tokens vs 1,048,576.

The Claude Sonnet 5 and Gemini 3.8 Flash comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Claude Sonnet 5 or Gemini 3.8 Flash page. See also the complete list of AI model comparisons.