Skip to main content

Model comparison

Inkling vs Mistral Large 3

Data verified

Head-to-head evidence from 14 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
72/100
Margin
21.7pts
← winning
50.26/100
0 category wins0 category wins

Verified leaderboard positions: Inkling #17; Mistral Large 3 unranked

BenchAlign evidence: Inkling not scored; Mistral Large 3 supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Inkling and Mistral Large 3 share 14 comparable benchmark results. 0 of 8 categories are comparable. 18 results are unique to Inkling; 3 to Mistral Large 3.

Updated July 16, 2026
Shared results
14
Inkling only
18
Mistral Large 3 only
3
Comparable categories
0 / 8

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

Confidence note. This is a partial-evidence comparison with 14 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.

Inkling is priced at $1.87 input / $4.68 output per 1M tokens, versus $0.50 input / $1.50 output per 1M tokens for Mistral Large 3. Inkling has the larger context window at 1M, compared with 128K for Mistral Large 3.

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 Inkling and Mistral Large 3
CategoryInklingΔMistral Large 3
AgenticInkling69.4MarginNo overlapMistral Large 3Not measured
CodingInkling68.6MarginNo overlapMistral Large 3Not measured
KnowledgeInkling51.7MarginNo overlapMistral Large 3Not measured
MathInkling97.1MarginNo overlapMistral Large 3Not measured
MultimodalInkling76.5MarginNo overlapMistral Large 3Not measured
Inst. FollowingInkling79.8MarginNo overlapMistral Large 3Not measured

Operational comparison

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

MetricInklingMistral Large 3Comparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputMistral Large 3$0.5 input / $1.5 outputMistral Large 3 has the lower combined listed price.
Generation speedtokens per secondInklingNot availableMistral Large 348 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableMistral Large 31.04 sA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MMistral Large 3128KInkling lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkInklingMistral Large 3Result
Terminal-Bench 2.0Source 63.8%Not comparable
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
AA Agentic IndexSource 32.3%5.5%Inkling leads
GDPval-AASource 36.9%6.6%Inkling leads
GDPval-AASource 1239633Inkling leads
AA BriefcaseSource 836Not comparable
AA Tau3 BankingSource 23.7%Not comparable
τ²-bench resultsSource 24.6%Not comparable
Coding
BenchmarkInklingMistral Large 3Result
SWE-bench VerifiedSource 77.6%Not comparable
SWE-bench ProSource 54.3%Not comparable
Terminal-Bench 2.0Source 63.8%Not comparable
AA Coding IndexSource 52.1%20.1%Inkling leads
AA-SciCodeSource 46.1%36.2%Inkling leads
Terminal-Bench HardSource 15.9%Not comparable
Reasoning
BenchmarkInklingMistral Large 3Result
AA-LCRSource 63.3%34.7%Inkling leads
CritPtSource 5.4%0.0%Inkling leads
Knowledge
BenchmarkInklingMistral Large 3Result
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
Artificial Analysis Intelligence IndexSource 40.7%15.9%Inkling leads
AA-GPQA DiamondSource 87.2%68.0%Inkling leads
AA-HLESource 29.7%4.1%Inkling leads
AA-Omniscience IndexSource 2.1%-39.4%Inkling leads
AA-Omniscience AccuracySource 40.0%24.1%Inkling leads
AA-Omniscience Hallucination RateSource 63.1%83.7%Inkling leads
Math
BenchmarkInklingMistral Large 3Result
AIME26Source 97.1%Not comparable
Multimodal
BenchmarkInklingMistral Large 3Result
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
AA-MMMU-ProSource 73.5%55.7%Inkling leads
Inst. Following
BenchmarkInklingMistral Large 3Result
IFBenchSource 79.8%Not comparable
AA-IFBenchSource 36.2%Not comparable
Frequently Asked Questions (3)

Can I compare Inkling and Mistral Large 3 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 Inkling and Mistral Large 3 today?

Inkling: $1.87 input / $4.68 output per 1M tokens Mistral Large 3: $0.50 input / $1.50 output per 1M tokens 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.

Inkling
API / mo$4,913
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Mistral Large 3
API / mo$1,500
Self-host / mo$9,110
Break-even380M/day
Model the full break-even

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.