Enter opens the highlighted result. Esc closes.

Claude Opus 4.7 vs Ministral 3 14B 2512

Claude Opus 4.7 leads Ministral 3 14B 2512 on the Artificial Analysis Intelligence Index, 40.7 to 6.0, and Ministral 3 14B 2512 costs 125.0x less per output token ($0.20 vs $25.00 per million). Updated October 22, 2026; 3 benchmarks have a result for both.

Replace Claude Opus 4.7 Replace Ministral 3 14B 2512
Claude Opus 4.7Anthropic
Coding
67.5
Overall
71.6
Output $/M
$25.00
3
Ministral 3 14B 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.20
0
vs boards won of 3 shared

Claude Opus 4.7 or Ministral 3 14B 2512: which to pick

Only Claude Opus 4.7 has a coding score, 67.5 on the Vibe Coding Index; Ministral 3 14B 2512 has none, so the two cannot be ranked on coding.

Pick Ministral 3 14B 2512 for output tokens 125.0x cheaper ($0.20 vs $25.00 per million).

Model AClaude Opus 4.7Anthropic67.5/1004 independent benchmarks$2.95 per solved taskModel BMinistral 3 14B 2512Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
3
Claude Opus 4.7 only
106
Ministral 3 14B 2512 only
4
Like-for-like categories
3 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
Claude Opus 4.7 67.5 from 4 benchmarks, Ministral 3 14B 2512 not benchmarked.
Widest category
Coding, 59.2 points apart on average over 1 shared benchmark.
Widest single gap
AA Coding Index: Claude Opus 4.7 73.6 against Ministral 3 14B 2512 14.4, 59.2 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.7 $25.00 against Ministral 3 14B 2512 $0.20 per million output tokens, 125.0x apart.
Context window
Claude Opus 4.7 takes 1M tokens, Ministral 3 14B 2512 262K.

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
CategoryClaude Opus 4.7BarsMinistral 3 14B 2512Ties
Coding10
Intelligence10
Agentic work10
All shared boards30
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
Coding benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
LMArena WebDev1558Not measuredOnly Claude Opus 4.7 measured
AA Coding Index73.614.4Claude Opus 4.7
LiveCodeBench (Vals AI)85.1%Not measuredOnly Claude Opus 4.7 measured
SWE-bench Verified (Vals AI)82.0%Not measuredOnly Claude Opus 4.7 measured
Vibe Code Bench (Vals AI)71.0%Not measuredOnly Claude Opus 4.7 measured
Code migration (Vals AI)43.9%Not measuredOnly Claude Opus 4.7 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Opus 4.7 measured
Terminal-Bench 2.1 (Vals AI)68.5%Not measuredOnly Claude Opus 4.7 measured
Terminal-Bench Hard (Artificial Analysis run)54.5%Not measuredOnly Claude Opus 4.7 measured
Terminal-Bench80.2%Not measuredOnly Claude Opus 4.7 measured
FrontierCode38.5%Not measuredOnly Claude Opus 4.7 measured
GSO-Bench44.1%Not measuredOnly Claude Opus 4.7 measured
WeirdML76.4%Not measuredOnly Claude Opus 4.7 measured
MirrorCode31.1%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: coding1519Not measuredOnly Claude Opus 4.7 measured
LMArena Text: software and IT1516Not measuredOnly Claude Opus 4.7 measured
LMArena WebDev: React1560Not measuredOnly Claude Opus 4.7 measured
LMArena WebDev: HTML1554Not measuredOnly Claude Opus 4.7 measured
LMArena WebDev: from an image1577Not measuredOnly Claude Opus 4.7 measured
SWE Atlas: Codebase QnA40.3%Not measuredOnly Claude Opus 4.7 measured
SWE Atlas: Refactoring48.6%Not measuredOnly Claude Opus 4.7 measured
SWE Atlas: Test Writing38.5%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
AA Intelligence Index40.76.0Claude Opus 4.7
Epoch Capabilities Index156.8Not measuredOnly Claude Opus 4.7 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
AA Agentic Index38.61.1Claude Opus 4.7
Finance Agent (Vals AI)51.5%Not measuredOnly Claude Opus 4.7 measured
Tax Agent Bench (Vals AI)23.7%Not measuredOnly Claude Opus 4.7 measured
Legal Research Bench (Vals AI)38.5%Not measuredOnly Claude Opus 4.7 measured
Excel Modeling Benchmark (Vals AI)63.7%Not measuredOnly Claude Opus 4.7 measured
τ²-Bench Telecom88.6%Not measuredOnly Claude Opus 4.7 measured
APEX-Agents49.2%Not measuredOnly Claude Opus 4.7 measured
OSWorld 2.018.2%Not measuredOnly Claude Opus 4.7 measured
PostTrainBench28.6%Not measuredOnly Claude Opus 4.7 measured
Vending-Bench 2$10,937Not measuredOnly Claude Opus 4.7 measured
LMArena Search1230Not measuredOnly Claude Opus 4.7 measured
MCP Atlas79.1%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 30 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
Reasoning benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
GPQA Diamond90.2%Not measuredOnly Claude Opus 4.7 measured
MMMU Pro (Vals AI)85.5%Not measuredOnly Claude Opus 4.7 measured
GPQA Diamond (Artificial Analysis run)91.4%Not measuredOnly Claude Opus 4.7 measured
Humanity's Last Exam (Artificial Analysis run)42.3%Not measuredOnly Claude Opus 4.7 measured
GPQA Diamond (Epoch AI run)90.2%Not measuredOnly Claude Opus 4.7 measured
ARC-AGI93.5%Not measuredOnly Claude Opus 4.7 measured
ARC-AGI-275.8%Not measuredOnly Claude Opus 4.7 measured
SimpleBench61.7%Not measuredOnly Claude Opus 4.7 measured
Chess puzzles41.0%Not measuredOnly Claude Opus 4.7 measured
Mystery game puzzles28.0%Not measuredOnly Claude Opus 4.7 measured
EBR-bench19.0%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: hard prompts1506Not measuredOnly Claude Opus 4.7 measured
LMArena Text: expert1521Not measuredOnly Claude Opus 4.7 measured
LMArena Text: hard prompts in English1508Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: diagrams1336Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: homework1337Not measuredOnly Claude Opus 4.7 measured
Kagi LLM Benchmark80.7%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 6 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
AIME96.3%Not measuredOnly Claude Opus 4.7 measured
OTIS Mock AIME97.8%Not measuredOnly Claude Opus 4.7 measured
FrontierMath, tiers 1 to 370.2%Not measuredOnly Claude Opus 4.7 measured
FrontierMath, tier 431.7%Not measuredOnly Claude Opus 4.7 measured
ProofBench54.0%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: math1498Not measuredOnly Claude Opus 4.7 measured
LMArena Text: mathematical work1509Not measuredOnly Claude Opus 4.7 measured
MathArena20.4%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 6 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
Knowledge benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
MMLU Pro89.9%Not measuredOnly Claude Opus 4.7 measured
LegalBench (Vals AI)85.3%Not measuredOnly Claude Opus 4.7 measured
CaseLaw (Vals AI)68.4%Not measuredOnly Claude Opus 4.7 measured
CorpFin (Vals AI)66.1%Not measuredOnly Claude Opus 4.7 measured
TaxEval (Vals AI)75.3%Not measuredOnly Claude Opus 4.7 measured
MortgageTax (Vals AI)70.3%Not measuredOnly Claude Opus 4.7 measured
MedCode (Vals AI)54.9%Not measuredOnly Claude Opus 4.7 measured
SimpleQA Verified51.7%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: science1508Not measuredOnly Claude Opus 4.7 measured
LMArena Text: medicine and healthcare1495Not measuredOnly Claude Opus 4.7 measured
LMArena Text: legal and government1504Not measuredOnly Claude Opus 4.7 measured
LMArena Text: business and finance1490Not measuredOnly Claude Opus 4.7 measured
FACTS Benchmark Suite45.5%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Web design benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
Design Arena: websitesNot measured1081Only Ministral 3 14B 2512 measured
Design Arena: game devNot measured1037Only Ministral 3 14B 2512 measured
Design Arena: 3DNot measured989Only Ministral 3 14B 2512 measured
Design Arena: all code categoriesNot measured1064Only Ministral 3 14B 2512 measured
Neither model has a result on the other 5 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index35 boards, none shared
General benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
SAGE (Vals AI)56.1%Not measuredOnly Claude Opus 4.7 measured
MedScribe (Vals AI)83.0%Not measuredOnly Claude Opus 4.7 measured
Vals Multimodal Index67.4%Not measuredOnly Claude Opus 4.7 measured
IFBench58.6%Not measuredOnly Claude Opus 4.7 measured
Long context reasoning (AA-LCR)78.7%Not measuredOnly Claude Opus 4.7 measured
DTBench94.7%Not measuredOnly Claude Opus 4.7 measured
LMCA52.2%Not measuredOnly Claude Opus 4.7 measured
Furniture assembly33.3%Not measuredOnly Claude Opus 4.7 measured
ExploitBench26.5%Not measuredOnly Claude Opus 4.7 measured
LMArena Text1490Not measuredOnly Claude Opus 4.7 measured
LMArena Text: instruction following1498Not measuredOnly Claude Opus 4.7 measured
LMArena Text: creative writing1486Not measuredOnly Claude Opus 4.7 measured
LMArena Vision1317Not measuredOnly Claude Opus 4.7 measured
LMArena Text: English1496Not measuredOnly Claude Opus 4.7 measured
LMArena Text: non-English1480Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Chinese1531Not measuredOnly Claude Opus 4.7 measured
LMArena Text: German1495Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Japanese1474Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Korean1464Not measuredOnly Claude Opus 4.7 measured
LMArena Text: French1503Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Spanish1494Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Russian1494Not measuredOnly Claude Opus 4.7 measured
LMArena Text: Polish1489Not measuredOnly Claude Opus 4.7 measured
LMArena Text: multi-turn1505Not measuredOnly Claude Opus 4.7 measured
LMArena Text: longer queries1505Not measuredOnly Claude Opus 4.7 measured
LMArena Text: writing and language1492Not measuredOnly Claude Opus 4.7 measured
LMArena Text: entertainment and media1474Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: English1322Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: Chinese1371Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: reading text1327Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: humor1309Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: recognizing things1278Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: creative writing1326Not measuredOnly Claude Opus 4.7 measured
LMArena Document1495Not measuredOnly Claude Opus 4.7 measured
EQ-Bench 41311Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.7 and Ministral 3 14B 2512
BenchmarkClaude Opus 4.7Ministral 3 14B 2512Leader
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

Claude Opus 4.7$0.018Fits in one request
Ministral 3 14B 2512$0.0003Fits in one request

Ministral 3 14B 2512 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.7$0.325Fits in one request
Ministral 3 14B 2512$0.011Fits in one request

Ministral 3 14B 2512 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.7$1.25Fits in one request
Ministral 3 14B 2512$0.042Fits in one request

Ministral 3 14B 2512 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 Claude Opus 4.7 and Ministral 3 14B 2512
SpecificationAnthropic Claude Opus 4.7Mistral Ministral 3 14B 2512
MakerAnthropicMistral AI
WeightsNo public weights listedOpen weights
ReleasedApril 16, 2026December 2, 2025
Context window1M262K
Input $/Mtok$5.00$0.20
Output $/Mtok$25.00$0.20
Coding index67.5Not benchmarked
Independent measurements behind it40
Cost per solved task$2.95Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.7 better than Ministral 3 14B 2512 for coding?

Only Claude Opus 4.7 has a coding score, 67.5 on the Vibe Coding Index; Ministral 3 14B 2512 has none, so the two cannot be ranked on coding. Pick Ministral 3 14B 2512 for output tokens 125.0x cheaper ($0.20 vs $25.00 per million).

Which is cheaper, Claude Opus 4.7 or Ministral 3 14B 2512?

Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; Ministral 3 14B 2512 costs $0.20 and $0.20. Cost per solved task is known for Claude Opus 4.7 only.

Which has the bigger context window, Claude Opus 4.7 or Ministral 3 14B 2512?

Claude Opus 4.7, with 1M tokens against 262K.

How many benchmarks is the Claude Opus 4.7 vs Ministral 3 14B 2512 comparison based on?

3 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.7's coding index rests on 4 independent benchmarks and Ministral 3 14B 2512's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next