Model comparison

GPT-6.1 Sol vs Mistral Medium

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 36.3 on the Noometry Index.

Last verified October 10, 2026. 19 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Mistral Medium

Mistral AI

36.3

Rank #218 Confirmed

Summary

They share 19 benchmarks with published results for both. GPT-6.1 Sol scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 28.1.
The biggest single-benchmark swing is ProofBench: 99% for GPT-6.1 Sol and 9% for Mistral Medium.
Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
GPT-6.1 Sol accepts more context: 1.05M tokens versus 262K.
Mistral Medium has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 Sol and Mistral Medium specifications
	GPT-6.1 Sol	Mistral Medium
Provider	OpenAI	Mistral AI
Noometry Index	65.6	36.3
Released	2026-09-29	2023-12-11
Weights	Proprietary	Open
Context window	1.05M	262K
Max output	128K	262K
Input $ / M tokens	$2	$1.50
Output $ / M tokens	$10	$7.50
Results tracked	34	36

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-6.1 Sol leads

GPT-6.1 Sol: 63.2 (#8), Mistral Medium: 34.2 (#243)

Coding benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
FrontierCode	50.2%	8%
SciCode	55.8%	40.2%
LMArena Coding	1487	1434
DeepSWE	75.2%	—
LMArena WebDev	1755	—
WeirdML	—	43.7%
ALE-Bench	—	763.98

Agentic & Tool Use GPT-6.1 Sol leads

GPT-6.1 Sol: 39.6 (#26), Mistral Medium: 28.3 (#90)

Agentic & Tool Use benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
APEX-Agents	60%	—
Berkeley Function Calling Leaderboard	—	37.7%
GDP.pdf	32%	—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Mistral Medium: 24.0 (#167)

Reasoning benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
CritPt	31.7%	0%
LMArena Hard Prompts	1466	1426
ARC-AGI-2	94.2%	—
Kagi LLM Benchmark	—	50%
NYT Connections (extended)	95.5%	—
ARC-AGI-1	98.5%	—
Chess Puzzles	61%	—
EBR-Bench	54.3%	—
Mystery Game Puzzles	80%	—
DTBench	—	75.5%
LMCA	—	26.1%
Surface Evolver Bench	—	26.9%
Epoch Capabilities Index	166.09	—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Mistral Medium: 28.1 (#245)

Math benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
OTIS Mock AIME 2024-2025	100%	32.2%
ProofBench	99%	9%
LMArena Math	1464	1408
FrontierMath (Tiers 1-3)	93.7%	—
FrontierMath Tier 4	100%	—
MATH Level 5	—	81.6%
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Mistral Medium: 25.0 (#265)

Knowledge benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
GPQA Diamond	95.4%	59.5%
LMArena Expert	1502	1408
Humanity's Last Exam	—	4.5%
SimpleQA Verified	73.9%	—
Vectara Hallucination Rate	—	22.7%

Multimodal GPT-6.1 Sol leads

GPT-6.1 Sol: 52.7 (#5), Mistral Medium: 35.3 (#88)

Multimodal benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
LMArena Vision	1288	1172
Furniture Assembly	80%	—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Mistral Medium: 52.1 (#91)

Multilingual benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
LMArena Non-English	1438	1408
LMArena Chinese	1477	1447
LMArena Russian	1455	1411
LMArena French	—	1459
LMArena German	—	1432
LMArena Japanese	—	1378
LMArena Korean	—	1380
LMArena Spanish	—	1433

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Mistral Medium: 73.7 (#116)

Instruction Following benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
LMArena Instruction Following	1468	1398

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Mistral Medium: 42.9 (#114)

Long Context benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
LMArena Longer Query	1465	1406

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Mistral Medium: 60.0 (#103)

Writing & Preference benchmarks
Benchmark	GPT-6.1 Sol	Mistral Medium
LMArena Text	1447	1424
LMArena Creative Writing	1432	1391
LMArena Multi-Turn	1449	1418
Short-Story Creative Writing	—	77.3%

Frequently asked questions

Is GPT-6.1 Sol better than Mistral Medium?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 36.3 on the Noometry Index.

Which is cheaper, GPT-6.1 Sol or Mistral Medium?

Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is GPT-6.1 Sol or Mistral Medium better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 34.2 in the Noometry coding category.

Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 262K.

How many benchmarks do GPT-6.1 Sol and Mistral Medium share?

19 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Mistral Medium has 36.