Skip to main content

Model comparison

Claude 3 Haiku vs Gemini 3.6 Flash

Data verified

Head-to-head evidence from 10 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

21.39/100
No comparison
N/A
0 category wins0 category wins

Public leaderboard positions: Claude 3 Haiku #194 (Supported); Gemini 3.6 Flash unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3 Haiku and Gemini 3.6 Flash share 10 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to Claude 3 Haiku; 9 to Gemini 3.6 Flash.

Updated July 21, 2026
Shared results
10
Claude 3 Haiku only
2
Gemini 3.6 Flash only
9
Comparable categories
0 / 8

Benchmark data for Claude 3 Haiku and Gemini 3.6 Flash is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 10 shared benchmark results across 4 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Gemini 3.6 Flash is priced at $1.50 input / $7.50 output per 1M tokens, versus $0.25 input / $1.25 output per 1M tokens for Claude 3 Haiku. Gemini 3.6 Flash has the larger context window at 1M, compared with 200K for Claude 3 Haiku.

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 Haiku and Gemini 3.6 Flash
CategoryClaude 3 HaikuΔGemini 3.6 Flash
AgenticClaude 3 HaikuNot measuredMarginNo overlapGemini 3.6 Flash83.0

Operational comparison

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

MetricClaude 3 HaikuGemini 3.6 FlashComparison
Input / output priceUSD per 1M tokensClaude 3 Haiku$0.25 input / $1.25 outputGemini 3.6 Flash$1.5 input / $7.5 outputClaude 3 Haiku has the lower combined listed price.
Generation speedtokens per secondClaude 3 Haiku138 tok/sGemini 3.6 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude 3 Haiku1.16 sGemini 3.6 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude 3 Haiku200KGemini 3.6 Flash1MGemini 3.6 Flash lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
τ²-bench resultsSource 21.1%Not comparable
OSWorld-VerifiedSource 83%Not comparable
GDPval-AASource 1421Not comparable
AA Agentic IndexSource 38.7%Not comparable
GDPval-AASource 46.1%Not comparable
AA BriefcaseSource 961Not comparable
AA Tau3 BankingSource 24.5%Not comparable
aaTerminalBench21Source 77.5%Not comparable
Coding
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
AA-SciCodeSource 18.6%52.7%Gemini 3.6 Flash leads
deepSweSource 49%Not comparable
AA Coding IndexSource 69.2%Not comparable
Reasoning
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
AA-LCRSource 21.0%69.7%Gemini 3.6 Flash leads
CritPtSource 0.0%10.6%Gemini 3.6 Flash leads
Knowledge
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
Artificial Analysis Intelligence IndexSource 3.9%50.1%Gemini 3.6 Flash leads
AA-GPQA DiamondSource 37.4%92.8%Gemini 3.6 Flash leads
AA-HLESource 3.9%38.3%Gemini 3.6 Flash leads
AA-Omniscience IndexSource -47.6%23.5%Gemini 3.6 Flash leads
AA-Omniscience AccuracySource 17.2%50.2%Gemini 3.6 Flash leads
AA-Omniscience Hallucination RateSource 78.2%53.5%Gemini 3.6 Flash leads
Multimodal
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
AA-MMMU-ProSource 30.8%83.2%Gemini 3.6 Flash leads
Inst. Following
BenchmarkClaude 3 HaikuGemini 3.6 FlashResult
AA-IFBenchSource 36.1%Not comparable
Frequently Asked Questions (3)

Can I compare Claude 3 Haiku and Gemini 3.6 Flash on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Claude 3 Haiku and Gemini 3.6 Flash today?

Claude 3 Haiku: $0.25 input / $1.25 output per 1M tokens Gemini 3.6 Flash: $1.50 input / $7.50 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 21, 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.