Noometry

Model comparison

GPT-5.6 Terra vs Pixtral 12B

GPT-5.6 Terra has enough public results to be ranked (#17); Pixtral 12B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GPT-5.6 Terra OpenAI

59.2

Rank #17 Confirmed

Pixtral 12B Mistral AI

31.3

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. GPT-5.6 Terra scores higher in 1 category and Pixtral 12B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in multimodal, where GPT-5.6 Terra leads 47.3 to 23.9.
  • Pixtral 12B is cheaper at $0.15 / $0.15 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
  • GPT-5.6 Terra accepts more context: 1.05M tokens versus 128K.
  • Pixtral 12B has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 TerraPixtral 12B
ProviderOpenAIMistral AI
Noometry Index59.231.3
Released2026-07-092024-09-01
WeightsProprietaryOpen
Context window1.05M128K
Max output128K128K
Input $ / M tokens$2$0.15
Output $ / M tokens$12$0.15
Results tracked522

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

Category by category

Coding Not comparable

GPT-5.6 Terra: 57.7 (#19), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
DeepSWE69.6%—
FrontierCode41.3%—
CursorBench41.3%—
LMArena WebDev1522—
SciCode55%—
WeirdML78.3%—
LMArena Coding1484—
ALE-Bench1,951—

Agentic & Tool Use Not comparable

GPT-5.6 Terra: 40.1 (#25), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
APEX-Agents58.2%—
BALROG53.2%—
GDP.pdf24.7%—
Vending-Bench 27,343—

Reasoning Not comparable

GPT-5.6 Terra: 60.7 (#21), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
ARC-AGI-283.9%—
SimpleBench48.9%—
Kagi LLM Benchmark51.3%—
NYT Connections (extended)78.4%—
ARC-AGI-196.5%—
CritPt30%—
Chess Puzzles54%—
LMArena Hard Prompts1468—
Mystery Game Puzzles35%—
DTBench93.3%—
LMCA55%—
Surface Evolver Bench83.8%—
Epoch Capabilities Index159.62—

Math Not comparable

GPT-5.6 Terra: 81.6 (#12), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
FrontierMath (Tiers 1-3)86%—
FrontierMath Tier 470.7%—
OTIS Mock AIME 2024-202599.7%—
ProofBench74%—
LMArena Math1466—

Knowledge Not comparable

GPT-5.6 Terra: 61.2 (#30), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
GPQA Diamond93.3%—
SimpleQA Verified43.2%—
LMArena Expert1492—

Multimodal GPT-5.6 Terra leads

GPT-5.6 Terra: 47.3 (#11), Pixtral 12B: 23.9 (#127)

BenchmarkGPT-5.6 TerraPixtral 12B
LMArena Vision12711009
GeoBench—37%
Blueprint-Bench 230.8%—
Furniture Assembly54.2%—
LMArena Document1472—

Multilingual Not comparable

GPT-5.6 Terra: 54.4 (#44), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
LMArena Non-English1439—
LMArena Chinese1513—
LMArena French1471—
LMArena German1460—
LMArena Japanese1457—
LMArena Korean1425—
LMArena Russian1450—
LMArena Spanish1448—

Instruction Following Not comparable

GPT-5.6 Terra: 76.4 (#40), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
LMArena Instruction Following1454—

Long Context Not comparable

GPT-5.6 Terra: 44.4 (#68), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
LMArena Longer Query1451—

Writing & Preference Not comparable

GPT-5.6 Terra: 70.2 (#23), Pixtral 12B: —

BenchmarkGPT-5.6 TerraPixtral 12B
LMArena Text1447—
LMArena Creative Writing1410—
EQ-Bench Creative Writing1855—
EQ-Bench 41234—
LMArena Multi-Turn1449—

Frequently asked questions

Is GPT-5.6 Terra better than Pixtral 12B?

GPT-5.6 Terra has enough public results to be ranked (#17); Pixtral 12B does not yet, so treat this comparison as directional.

Which is cheaper, GPT-5.6 Terra or Pixtral 12B?

Pixtral 12B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; GPT-5.6 Terra lists at $2 and $12.

Which has the bigger context window?

GPT-5.6 Terra does, with 1.05M tokens against 128K.

How many benchmarks do GPT-5.6 Terra and Pixtral 12B share?

1 benchmark has published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Pixtral 12B has 2.

Related comparisons

Go deeper