Noometry

Model comparison

GPT-5.6 Terra vs Mistral Large

GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 31.9 on the Noometry Index. Mistral Large costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

GPT-5.6 Terra OpenAI

59.2

Rank #17 Confirmed

Mistral Large Mistral AI

31.9

Rank #263 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 18.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.7% for GPT-5.6 Terra and 8.5% for Mistral Large.
  • Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
  • GPT-5.6 Terra accepts more context: 1.05M tokens versus 131K.
  • Mistral Large has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 TerraMistral Large
ProviderOpenAIMistral AI
Noometry Index59.231.9
Released2026-07-092024-02-26
WeightsProprietaryOpen
Context window1.05M131K
Max output128K16K
Input $ / M tokens$2$2
Output $ / M tokens$12$6
Results tracked5251

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

Category by category

Coding GPT-5.6 Terra leads

GPT-5.6 Terra: 57.7 (#19), Mistral Large: 34.3 (#240)

BenchmarkGPT-5.6 TerraMistral Large
SciCode55%36.2%
LMArena Coding14841277
ALE-Bench1,951264.7
DeepSWE69.6%—
FrontierCode41.3%—
CursorBench41.3%—
LMArena WebDev1522—
WeirdML78.3%—
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use GPT-5.6 Terra leads

GPT-5.6 Terra: 40.1 (#25), Mistral Large: 28.6 (#89)

BenchmarkGPT-5.6 TerraMistral Large
APEX-Agents58.2%—
Berkeley Function Calling Leaderboard—38.4%
BALROG53.2%—
GDP.pdf24.7%—
Vending-Bench 27,343—

Reasoning GPT-5.6 Terra leads

GPT-5.6 Terra: 60.7 (#21), Mistral Large: 15.8 (#310)

BenchmarkGPT-5.6 TerraMistral Large
SimpleBench48.9%22.5%
CritPt30%0%
LMArena Hard Prompts14681257
DTBench93.3%65.1%
LMCA55%16.7%
Epoch Capabilities Index159.62128.52
ARC-AGI-283.9%—
Kagi LLM Benchmark51.3%—
NYT Connections (extended)78.4%—
ARC-AGI-196.5%—
Chess Puzzles54%—
LiveBench Reasoning—43.5%
Mystery Game Puzzles35%—
LiveBench Data Analysis—50.1%
Surface Evolver Bench83.8%—
ForecastBench—57.1
LiveBench—48.4%

Math GPT-5.6 Terra leads

GPT-5.6 Terra: 81.6 (#12), Mistral Large: 18.2 (#291)

BenchmarkGPT-5.6 TerraMistral Large
OTIS Mock AIME 2024-202599.7%8.5%
LMArena Math14661262
FrontierMath (Tiers 1-3)86%—
FrontierMath Tier 470.7%—
ProofBench74%—
Omni-MATH—28.1%
LiveBench Math—42.5%
MATH Level 5—50.3%
FrontierMath (Feb 2025 set)—0.3%

Knowledge GPT-5.6 Terra leads

GPT-5.6 Terra: 61.2 (#30), Mistral Large: 30.1 (#230)

BenchmarkGPT-5.6 TerraMistral Large
GPQA Diamond93.3%51.3%
LMArena Expert14921232
SimpleQA Verified43.2%—
MMLU-Pro—59.9%
Confabulations—21.4%
Vectara Hallucination Rate—4.5%
GPQA (HELM)—43.5%
MMLU—80%

Multimodal Not comparable

GPT-5.6 Terra: 47.3 (#11), Mistral Large: —

BenchmarkGPT-5.6 TerraMistral Large
LMArena Vision1271—
Blueprint-Bench 230.8%—
Furniture Assembly54.2%—
LMArena Document1472—

Multilingual GPT-5.6 Terra leads

GPT-5.6 Terra: 54.4 (#44), Mistral Large: 40.0 (#219)

BenchmarkGPT-5.6 TerraMistral Large
LMArena Non-English14391237
LMArena Chinese15131240
LMArena French14711325
LMArena German14601254
LMArena Japanese14571188
LMArena Korean14251202
LMArena Russian14501257
LMArena Spanish14481268

Instruction Following GPT-5.6 Terra leads

GPT-5.6 Terra: 76.4 (#40), Mistral Large: 67.9 (#191)

BenchmarkGPT-5.6 TerraMistral Large
LMArena Instruction Following14541249
LiveBench Instruction Following—67.9%
IFEval—87.7%

Long Context GPT-5.6 Terra leads

GPT-5.6 Terra: 44.4 (#68), Mistral Large: 38.3 (#199)

BenchmarkGPT-5.6 TerraMistral Large
LMArena Longer Query14511261

Writing & Preference GPT-5.6 Terra leads

GPT-5.6 Terra: 70.2 (#23), Mistral Large: 40.7 (#242)

BenchmarkGPT-5.6 TerraMistral Large
LMArena Text14471266
LMArena Creative Writing14101243
EQ-Bench Creative Writing1855985
LMArena Multi-Turn14491260
Short-Story Creative Writing—69%
WildBench—80.1%
EQ-Bench 41234—
LiveBench Language—39.4%

Frequently asked questions

Is GPT-5.6 Terra better than Mistral Large?

GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 31.9 on the Noometry Index. Mistral Large costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.

Which is cheaper, GPT-5.6 Terra or Mistral Large?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5.6 Terra lists at $2 and $12.

Is GPT-5.6 Terra or Mistral Large better for coding?

GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 34.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Terra does, with 1.05M tokens against 131K.

How many benchmarks do GPT-5.6 Terra and Mistral Large share?

27 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper