Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs Mistral Medium 3

Mistral Medium 3 leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 9.0 to 7.0, and Mistral Medium 3 costs 1.6x less per output token ($2.00 vs $3.20 per million). Updated October 21, 2026; 41 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace Mistral Medium 3
Nova Pro 1.0Amazon
Coding
No data
Overall
No data
Output $/M
$3.20
1
Mistral Medium 3Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
40
vs boards won of 41 shared

Nova Pro 1.0 or Mistral Medium 3: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Nova Pro 1.0 for a larger context window (300K against 131K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
Nova Pro 1.0 only
1
Mistral Medium 3 only
16
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Nova Pro 1.0 not benchmarked, Mistral Medium 3 not benchmarked.
Widest category
Web design, 35.4 points apart on average over 1 shared benchmark.
Widest single gap
Design Arena: websites: Nova Pro 1.0 796 against Mistral Medium 3 1079, 35.4 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against Mistral Medium 3 $2.00 per million output tokens, 1.6x apart.
Context window
Nova Pro 1.0 takes 300K tokens, Mistral Medium 3 131K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryNova Pro 1.0BarsMistral Medium 3Ties
Coding13
Intelligence01
Agentic work01
Reasoning05
Math04
Knowledge05
Web design01
General020
All shared boards140
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
Coding benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
LiveCodeBench (Artificial Analysis run)23.3%40.0%Mistral Medium 3
Terminal-Bench Hard (Artificial Analysis run)6.1%3.8%Nova Pro 1.0
LMArena Text: coding12701385Mistral Medium 3
LMArena Text: software and IT12711385Mistral Medium 3
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
AA Intelligence Index7.09.0Mistral Medium 3
Epoch Capabilities IndexNot measured134.0Only Mistral Medium 3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
τ²-Bench Telecom14.0%24.3%Mistral Medium 3
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
GPQA Diamond (Artificial Analysis run)49.9%57.8%Mistral Medium 3
Humanity's Last Exam (Artificial Analysis run)3.2%4.1%Mistral Medium 3
LMArena Text: hard prompts12461364Mistral Medium 3
LMArena Text: expert12111342Mistral Medium 3
LMArena Text: hard prompts in English12591374Mistral Medium 3
LMArena Vision: diagramsNot measured1155Only Mistral Medium 3 measured
LMArena Vision: homeworkNot measured1165Only Mistral Medium 3 measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
AA Math Index7.030.3Mistral Medium 3
AIME 2025 (Artificial Analysis run)7.0%30.3%Mistral Medium 3
LMArena Text: math12521353Mistral Medium 3
LMArena Text: mathematical work12611354Mistral Medium 3
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
MMLU Pro (Artificial Analysis run)69.1%76.0%Mistral Medium 3
MMLU82.0%Not measuredOnly Nova Pro 1.0 measured
LMArena Text: science12551381Mistral Medium 3
LMArena Text: medicine and healthcare12601381Mistral Medium 3
LMArena Text: legal and government12811384Mistral Medium 3
LMArena Text: business and finance12291352Mistral Medium 3
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
Design Arena: websites7961079Mistral Medium 3
Design Arena: UI componentsNot measured1024Only Mistral Medium 3 measured
Design Arena: game devNot measured1018Only Mistral Medium 3 measured
Design Arena: data vizNot measured1034Only Mistral Medium 3 measured
Design Arena: 3DNot measured1084Only Mistral Medium 3 measured
Design Arena: all code categoriesNot measured1069Only Mistral Medium 3 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
IFBench38.1%39.3%Mistral Medium 3
Long context reasoning (AA-LCR)21.0%31.3%Mistral Medium 3
DTBenchNot measured62.3%Only Mistral Medium 3 measured
LMArena Text12591370Mistral Medium 3
LMArena Text: instruction following12351338Mistral Medium 3
LMArena Text: creative writing12121343Mistral Medium 3
LMArena Vision9801157Mistral Medium 3
LMArena Text: English12761385Mistral Medium 3
LMArena Text: non-English12331353Mistral Medium 3
LMArena Text: Chinese12441374Mistral Medium 3
LMArena Text: German12431377Mistral Medium 3
LMArena Text: Japanese12001316Mistral Medium 3
LMArena Text: Korean12031304Mistral Medium 3
LMArena Text: French12711368Mistral Medium 3
LMArena Text: Spanish11821364Mistral Medium 3
LMArena Text: Russian12401359Mistral Medium 3
LMArena Text: PolishNot measured1371Only Mistral Medium 3 measured
LMArena Text: multi-turn12461384Mistral Medium 3
LMArena Text: longer queries12551360Mistral Medium 3
LMArena Text: writing and language12471352Mistral Medium 3
LMArena Text: entertainment and media12101335Mistral Medium 3
LMArena Vision: English9871172Mistral Medium 3
LMArena Vision: ChineseNot measured1161Only Mistral Medium 3 measured
LMArena Vision: reading textNot measured1154Only Mistral Medium 3 measured
LMArena Vision: humorNot measured1145Only Mistral Medium 3 measured
LMArena Vision: captioningNot measured1094Only Mistral Medium 3 measured
LMArena Vision: recognizing thingsNot measured1141Only Mistral Medium 3 measured
LMArena Vision: creative writingNot measured1146Only Mistral Medium 3 measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nova Pro 1.0 and Mistral Medium 3
BenchmarkNova Pro 1.0Mistral Medium 3Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Nova Pro 1.0$0.0024Fits in one request
Mistral Medium 3$0.0014Fits in one request

Mistral Medium 3 costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
Mistral Medium 3$0.026Fits in one request

Mistral Medium 3 costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
Mistral Medium 3$0.100Exceeds the context window

Mistral Medium 3 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Nova Pro 1.0 and Mistral Medium 3
SpecificationAmazon Nova Pro 1.0Mistral Medium 3
MakerAmazonMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedDecember 5, 2024May 7, 2025
Context window300K131K
Input $/Mtok$0.80$0.40
Output $/Mtok$3.20$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova Pro 1.0 better than Mistral Medium 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Pro 1.0 for a larger context window (300K against 131K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Nova Pro 1.0 or Mistral Medium 3?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova Pro 1.0 or Mistral Medium 3?

Nova Pro 1.0, with 300K tokens against 131K.

How many benchmarks is the Nova Pro 1.0 vs Mistral Medium 3 comparison based on?

41 benchmarks have a result for both models as of October 21, 2026. Nova Pro 1.0's coding index rests on 0 independent benchmarks and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next