Skip to main content

Model comparison

Mistral Large 3 vs Nova Pro

Data verified

Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

50.4/100
Margin
30.1pts
← winning
Amazon
20.32/100
0 category wins0 category wins

Public leaderboard positions: Mistral Large 3 #113 (Supported); Nova Pro #196 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Mistral Large 3 and Nova Pro share 12 comparable benchmark results. 0 of 8 categories are comparable. 4 results are unique to Mistral Large 3; 0 to Nova Pro.

Updated July 20, 2026
Shared results
12
Mistral Large 3 only
4
Nova Pro only
0
Comparable categories
0 / 8

Benchmark data for Mistral Large 3 and Nova Pro is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 6 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.

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.

MetricMistral Large 3Nova ProComparison
Input / output priceUSD per 1M tokensMistral Large 3$0.5 input / $1.5 outputNova ProNot availableA complete price comparison is not available.
Generation speedtokens per secondMistral Large 348 tok/sNova Pro141 tok/sNova Pro has the higher measured throughput.
First-answer latencyseconds to first tokenMistral Large 31.04 sNova Pro0.81 sNova Pro reaches the first token sooner.
Context windowmaximum listed tokensMistral Large 3128KNova Pro128KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkMistral Large 3Nova ProResult
AA Agentic IndexSource 5.5%Not comparable
τ²-bench resultsSource 24.6%14%Mistral Large 3 leads
GDPval-AASource 6.6%Not comparable
GDPval-AASource 633Not comparable
Coding
BenchmarkMistral Large 3Nova ProResult
AA Coding IndexSource 20.1%Not comparable
AA-SciCodeSource 36.2%20.8%Mistral Large 3 leads
Reasoning
BenchmarkMistral Large 3Nova ProResult
AA-LCRSource 34.7%19.0%Mistral Large 3 leads
CritPtSource 0.0%0.0%Tie
Knowledge
BenchmarkMistral Large 3Nova ProResult
Artificial Analysis Intelligence IndexSource 15.9%7.7%Mistral Large 3 leads
AA-GPQA DiamondSource 68.0%49.9%Mistral Large 3 leads
AA-HLESource 4.1%3.4%Mistral Large 3 leads
AA-Omniscience IndexSource -39.4%-47.6%Mistral Large 3 leads
AA-Omniscience AccuracySource 24.1%17.0%Mistral Large 3 leads
AA-Omniscience Hallucination RateSource 83.7%77.9%Nova Pro leads
Multimodal
BenchmarkMistral Large 3Nova ProResult
AA-MMMU-ProSource 55.7%44.3%Mistral Large 3 leads
Inst. Following
BenchmarkMistral Large 3Nova ProResult
AA-IFBenchSource 36.2%38.1%Nova Pro leads
Frequently Asked Questions (3)

Can I compare Mistral Large 3 and Nova Pro 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 Mistral Large 3 and Nova Pro today?

Mistral Large 3: $0.50 input / $1.50 output per 1M tokens Nova Pro: Pricing unavailable Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Mistral Large 3
API / mo$1,500
Self-host / mo$9,110
Break-even380M/day
Nova Pro
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

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.