Skip to main content

Model comparison

Claude 3 Haiku vs Mistral Large 2

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

21.39/100
Margin
20.4pts
winning →
41.77/100
0 category wins0 category wins

Public leaderboard positions: Claude 3 Haiku #194 (Supported); Mistral Large 2 #163 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3 Haiku and Mistral Large 2 share 11 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to Claude 3 Haiku; 0 to Mistral Large 2.

Updated July 20, 2026
Shared results
11
Claude 3 Haiku only
1
Mistral Large 2 only
0
Comparable categories
0 / 8

Benchmark data for Claude 3 Haiku and Mistral Large 2 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 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.

Claude 3 Haiku has the larger context window at 200K, compared with 128K for Mistral Large 2.

Category breakdown

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

Operational comparison

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

MetricClaude 3 HaikuMistral Large 2Comparison
Input / output priceUSD per 1M tokensClaude 3 Haiku$0.25 input / $1.25 outputMistral Large 2Not availableA complete price comparison is not available.
Generation speedtokens per secondClaude 3 Haiku138 tok/sMistral Large 238 tok/sClaude 3 Haiku has the higher measured throughput.
First-answer latencyseconds to first tokenClaude 3 Haiku1.16 sMistral Large 21.45 sClaude 3 Haiku reaches the first token sooner.
Context windowmaximum listed tokensClaude 3 Haiku200KMistral Large 2128KClaude 3 Haiku lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3 HaikuMistral Large 2Result
τ²-bench resultsSource 21.1%30.7%Mistral Large 2 leads
Coding
BenchmarkClaude 3 HaikuMistral Large 2Result
AA-SciCodeSource 18.6%29.2%Mistral Large 2 leads
Reasoning
BenchmarkClaude 3 HaikuMistral Large 2Result
AA-LCRSource 21.0%5.3%Claude 3 Haiku leads
CritPtSource 0.0%0.0%Tie
Knowledge
BenchmarkClaude 3 HaikuMistral Large 2Result
Artificial Analysis Intelligence IndexSource 3.9%9.2%Mistral Large 2 leads
AA-GPQA DiamondSource 37.4%48.6%Mistral Large 2 leads
AA-HLESource 3.9%4.0%Mistral Large 2 leads
AA-Omniscience IndexSource -47.6%-34.0%Mistral Large 2 leads
AA-Omniscience AccuracySource 17.2%20.1%Mistral Large 2 leads
AA-Omniscience Hallucination RateSource 78.2%67.8%Mistral Large 2 leads
Multimodal
BenchmarkClaude 3 HaikuMistral Large 2Result
AA-MMMU-ProSource 30.8%Not comparable
Inst. Following
BenchmarkClaude 3 HaikuMistral Large 2Result
AA-IFBenchSource 36.1%31.2%Claude 3 Haiku leads
Frequently Asked Questions (3)

Can I compare Claude 3 Haiku and Mistral Large 2 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 Mistral Large 2 today?

Claude 3 Haiku: $0.25 input / $1.25 output per 1M tokens Mistral Large 2: Pricing unavailable Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

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.