Skip to main content

Model comparison

Claude 3.5 Sonnet vs Gemini 2.5 Flash

Data verified

Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

47.74/100
Margin
0.4pts
winning →
48.09/100
0 category wins1 category wins

Public leaderboard positions: Claude 3.5 Sonnet #132 (Estimated); Gemini 2.5 Flash #130 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3.5 Sonnet and Gemini 2.5 Flash share 2 comparable benchmark results. 1 of 8 categories are comparable. 2 results are unique to Claude 3.5 Sonnet; 13 to Gemini 2.5 Flash.

Updated July 20, 2026
Shared results
2
Claude 3.5 Sonnet only
2
Gemini 2.5 Flash only
13
Comparable categories
1 / 8

Pick Gemini 2.5 Flash if you want the stronger benchmark profile. Claude 3.5 Sonnet only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemini 2.5 Flash has the cleaner BenchAlign overall profile here, landing at 48.09 versus 47.74. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemini 2.5 Flash's sharpest advantage is in mathematics, where it averages 4.7 against 1.6. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 0.000% to 4.167%.

Claude 3.5 Sonnet is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.30 input / $2.50 output per 1M tokens for Gemini 2.5 Flash. That is roughly 6.0x on output cost alone. Gemini 2.5 Flash gives you the larger context window at 1M, compared with 200K for Claude 3.5 Sonnet.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude 3.5 Sonnet and Gemini 2.5 Flash
CategoryClaude 3.5 SonnetΔGemini 2.5 Flash
MathClaude 3.5 Sonnet1.6Margin 3.1Gemini 2.5 Flash4.7
CodingClaude 3.5 Sonnet49.0MarginNo overlapGemini 2.5 FlashNot measured
KnowledgeClaude 3.5 Sonnet59.4MarginNo overlapGemini 2.5 FlashNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude 3.5 SonnetB · Gemini 2.5 Flash
  1. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 0.000%B 4.167%
    Winner: Gemini 2.5 FlashΔ 4.2
    FrontierMath v2 (Tier 4): Claude 3.5 Sonnet scored 0.000%; Gemini 2.5 Flash scored 4.167%. Gemini 2.5 Flash wins this benchmark.
  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 2.069%B 4.844%
    Winner: Gemini 2.5 FlashΔ 2.8
    FrontierMath v2 (Tiers 1-3): Claude 3.5 Sonnet scored 2.069%; Gemini 2.5 Flash scored 4.844%. Gemini 2.5 Flash wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude 3.5 SonnetGemini 2.5 FlashComparison
Input / output priceUSD per 1M tokensClaude 3.5 Sonnet$3 input / $15 outputGemini 2.5 Flash$0.3 input / $2.5 outputGemini 2.5 Flash has the lower combined listed price.
Generation speedtokens per secondClaude 3.5 SonnetNot availableGemini 2.5 Flash221 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude 3.5 SonnetNot availableGemini 2.5 Flash0.50 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude 3.5 Sonnet200KGemini 2.5 Flash1MGemini 2.5 Flash lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
τ²-bench resultsSource 14.9%Not comparable
Coding
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
SWE-bench VerifiedSource 49%Not comparable
AA-SciCodeSource 29.1%Not comparable
Reasoning
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
AA-LCRSource 45.9%Not comparable
CritPtSource 1.4%Not comparable
Knowledge
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
GPQASource 59.4%Not comparable
Artificial Analysis Intelligence IndexSource 14.1%Not comparable
AA-GPQA DiamondSource 68.3%Not comparable
AA-HLESource 5.1%Not comparable
AA-Omniscience IndexSource -42.0%Not comparable
AA-Omniscience AccuracySource 26.5%Not comparable
AA-Omniscience Hallucination RateSource 93.3%Not comparable
MathGemini 2.5 Flash wins
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
FrontierMath v2 (Tiers 1-3)Source 2.069%4.844%Gemini 2.5 Flash leads
FrontierMath v2 (Tier 4)Source 0.000%4.167%Gemini 2.5 Flash leads
Multimodal
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
AA-MMMU-ProSource 65.5%Not comparable
Design Arena WebsiteSource 1148Not comparable
Inst. Following
BenchmarkClaude 3.5 SonnetGemini 2.5 FlashResult
AA-IFBenchSource 39.0%Not comparable
Frequently Asked Questions (2)

Which is better, Claude 3.5 Sonnet or Gemini 2.5 Flash?

Gemini 2.5 Flash is ahead on BenchLM's BenchAlign leaderboard, 48.09 to 47.74. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 0.000% and 4.167%.

Which is better for math, Claude 3.5 Sonnet or Gemini 2.5 Flash?

Gemini 2.5 Flash has the edge for math in this comparison, averaging 4.7 versus 1.6. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.