Inkling-Small vs Mistral Large 4: Specs & Benchmark Comparison

Inkling-Small is developed by Thinking Machines Lab, while Mistral Large 4 comes from Mistral AI. Inkling-Small was released in July 2026, and Mistral Large 4 followed 3 months later in October 2026. Mistral Large 4 is the larger model at roughly 1.1 trillion parameters, against 276 billion for Inkling-Small.

The two models share 2 published benchmarks. Mistral Large 4 leads on 2 of them. The widest gaps are on SciCode, where Mistral Large 4 scores 91.8% against 48.7%; AA-Briefcase, where Mistral Large 4 scores 46.4% against 30.6%. Averaged across everything we track, Inkling-Small sits at 60.3% and Mistral Large 4 at 60.4%.

Inkling-Small is the cheaper API at $0.30 per million input tokens and $1.20 per million output tokens, roughly 2 times cheaper than Mistral Large 4 at $0.68 and $2.09. Mistral Large 4 takes the larger context window at 1M tokens, compared with 256K for Inkling-Small. Inkling-Small accepts text, images, and audio as input, while Mistral Large 4 accepts text and images. On tooling, only Mistral Large 4 supports function calling and only Mistral Large 4 offers structured output.

CharacteristicInkling-SmallMistral Large 4
CompanyThinking Machines LabMistral AI
Release DateJuly 30, 2026October 6, 2026
Parameters276B1.1T
MultimodalYesYes
Context (input)256K1.0M
Context (output)256K—
Input Price / 1M$0.30$0.68
Output Price / 1M$1.20$2.09
Average Score60.3%60.4%
Benchmarks
SciCode48.7%91.8%
AA-Briefcase30.6%46.4%

Visual Benchmark Comparison

Inkling-Small
Mistral Large 4
SciCode0.5 vs 0.9
0.5
0.9
AA-Briefcase0.3 vs 0.5
0.3
0.5

Verdict

Mistral Large 4 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Inkling-Small — 0.6, Mistral Large 4 — 0.6.

API Cost

Inkling-Small is 1.8x cheaper: input $0.30/1M vs $0.68/1M tokens.

Context Window

Mistral Large 4 supports a larger context: 1M vs 256K tokens.

Recency

Mistral Large 4 is newer: released 10/6/2026 vs 7/30/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Inkling-Small or Mistral Large 4?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Inkling-Small or Mistral Large 4?
Inkling-Small is cheaper for input: $0.30 per 1M tokens vs $0.68.
Which has a larger context window — Inkling-Small or Mistral Large 4?
Mistral Large 4 supports a larger context: 1,048,576 tokens vs 256,000.

The Inkling-Small and Mistral Large 4 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Inkling-Small or Mistral Large 4 page. See also the complete list of AI model comparisons.