Noometry

Model comparison

GPT-5.6 Terra vs Step 3

GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 40.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-5.6 Terra OpenAI

59.2

Rank #17 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and Step 3 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 37.6.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 51.3% for GPT-5.6 Terra and 62.3% for Step 3.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 TerraStep 3
ProviderOpenAIStepFun
Noometry Index59.240.5
Released2026-07-09—
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$12—
Results tracked5217

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), Step 3: 40.1 (#147)

BenchmarkGPT-5.6 TerraStep 3
LMArena Coding14841367
DeepSWE69.6%—
FrontierCode41.3%—
CursorBench41.3%—
LMArena WebDev1522—
SciCode55%—
WeirdML78.3%—
ALE-Bench1,951—

Agentic & Tool Use Not comparable

GPT-5.6 Terra: 40.1 (#25), Step 3: —

BenchmarkGPT-5.6 TerraStep 3
APEX-Agents58.2%—
BALROG53.2%—
GDP.pdf24.7%—
Vending-Bench 27,343—

Reasoning GPT-5.6 Terra leads

GPT-5.6 Terra: 60.7 (#21), Step 3: 28.4 (#105)

BenchmarkGPT-5.6 TerraStep 3
Kagi LLM Benchmark51.3%62.3%
LMArena Hard Prompts14681355
ARC-AGI-283.9%—
SimpleBench48.9%—
NYT Connections (extended)78.4%—
ARC-AGI-196.5%—
CritPt30%—
Chess Puzzles54%—
Mystery Game Puzzles35%—
DTBench93.3%—
LMCA55%—
Surface Evolver Bench83.8%—
Epoch Capabilities Index159.62—

Math GPT-5.6 Terra leads

GPT-5.6 Terra: 81.6 (#12), Step 3: 37.6 (#148)

BenchmarkGPT-5.6 TerraStep 3
LMArena Math14661366
FrontierMath (Tiers 1-3)86%—
FrontierMath Tier 470.7%—
OTIS Mock AIME 2024-202599.7%—
ProofBench74%—

Knowledge GPT-5.6 Terra leads

GPT-5.6 Terra: 61.2 (#30), Step 3: 36.8 (#164)

BenchmarkGPT-5.6 TerraStep 3
LMArena Expert14921333
GPQA Diamond93.3%—
SimpleQA Verified43.2%—

Multimodal GPT-5.6 Terra leads

GPT-5.6 Terra: 47.3 (#11), Step 3: 35.5 (#86)

BenchmarkGPT-5.6 TerraStep 3
LMArena Vision12711177
Blueprint-Bench 230.8%—
Furniture Assembly54.2%—
LMArena Document1472—

Multilingual GPT-5.6 Terra leads

GPT-5.6 Terra: 54.4 (#44), Step 3: 46.3 (#159)

BenchmarkGPT-5.6 TerraStep 3
LMArena Non-English14391327
LMArena Chinese15131397
LMArena German14601371
LMArena Korean14251269
LMArena Russian14501331
LMArena Spanish14481371
LMArena French1471—
LMArena Japanese1457—

Instruction Following GPT-5.6 Terra leads

GPT-5.6 Terra: 76.4 (#40), Step 3: 70.4 (#164)

BenchmarkGPT-5.6 TerraStep 3
LMArena Instruction Following14541332

Long Context GPT-5.6 Terra leads

GPT-5.6 Terra: 44.4 (#68), Step 3: 40.3 (#157)

BenchmarkGPT-5.6 TerraStep 3
LMArena Longer Query14511326

Writing & Preference GPT-5.6 Terra leads

GPT-5.6 Terra: 70.2 (#23), Step 3: 54.3 (#151)

BenchmarkGPT-5.6 TerraStep 3
LMArena Text14471350
LMArena Creative Writing14101321
LMArena Multi-Turn14491341
EQ-Bench Creative Writing1855—
EQ-Bench 41234—

Frequently asked questions

Is GPT-5.6 Terra better than Step 3?

GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 40.5 on the Noometry Index.

Is GPT-5.6 Terra or Step 3 better for coding?

GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 40.1 in the Noometry coding category.

How many benchmarks do GPT-5.6 Terra and Step 3 share?

17 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper