Noometry

Model comparison

GPT-5.2 Codex vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 42.2 on the Noometry Index.

Last verified . 1 shared benchmarks.

GPT-5.2 Codex OpenAI

42.2

Rank #107 Reported

Inkling-Small Thinking Machines Lab

46.5

Rank #57 Confirmed

Summary

  • They share 1 benchmark with published results for both. GPT-5.2 Codex scores higher in 1 category and Inkling-Small in 0 categories; one gap is clear of the uncertainty.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
  • Inkling-Small accepts more context: 524K tokens versus 400K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 CodexInkling-Small
ProviderOpenAIThinking Machines Lab
Noometry Index42.246.5
Released2025-12-182026-07-15
WeightsProprietaryOpen
Context window400K524K
Max output128K1.05M
Input $ / M tokens$1.75$0.45
Output $ / M tokens$14$1.20
Results tracked533

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

Category by category

Coding GPT-5.2 Codex leads

GPT-5.2 Codex: 45.4 (#66), Inkling-Small: 43.3 (#80)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena WebDev13391408
SWE-bench Verified (bash only)72.8%—
SWE-bench Multilingual66.3%—
SciCode—48.7%
LMArena Coding—1451
ALE-Bench1,300—

Agentic & Tool Use Not comparable

GPT-5.2 Codex: 40.7 (#20), Inkling-Small: —

BenchmarkGPT-5.2 CodexInkling-Small
Terminal-Bench66.5%—

Reasoning Not comparable

GPT-5.2 Codex: —, Inkling-Small: 39.0 (#53)

BenchmarkGPT-5.2 CodexInkling-Small
ARC-AGI-2—40.1%
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
LMArena Hard Prompts—1424
Mystery Game Puzzles—6%
Epoch Capabilities Index—150.13

Math Not comparable

GPT-5.2 Codex: —, Inkling-Small: 44.9 (#65)

BenchmarkGPT-5.2 CodexInkling-Small
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
OTIS Mock AIME 2024-2025—90%
ProofBench—6%
LMArena Math—1453

Knowledge Not comparable

GPT-5.2 Codex: —, Inkling-Small: 48.3 (#71)

BenchmarkGPT-5.2 CodexInkling-Small
GPQA Diamond—88.5%
SimpleQA Verified—19.1%
LMArena Expert—1442

Multimodal Not comparable

GPT-5.2 Codex: —, Inkling-Small: 38.4 (#59)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena Vision—1235

Multilingual Not comparable

GPT-5.2 Codex: —, Inkling-Small: 51.7 (#102)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena Non-English—1400
LMArena Chinese—1458
LMArena French—1438
LMArena German—1412
LMArena Japanese—1399
LMArena Korean—1355
LMArena Russian—1392
LMArena Spanish—1426

Instruction Following Not comparable

GPT-5.2 Codex: —, Inkling-Small: 73.9 (#112)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena Instruction Following—1397

Long Context Not comparable

GPT-5.2 Codex: —, Inkling-Small: 42.7 (#113)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena Longer Query—1401

Writing & Preference Not comparable

GPT-5.2 Codex: —, Inkling-Small: 59.8 (#102)

BenchmarkGPT-5.2 CodexInkling-Small
LMArena Text—1413
LMArena Creative Writing—1330
EQ-Bench Creative Writing—1491
LMArena Multi-Turn—1420

Frequently asked questions

Is GPT-5.2 Codex better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 42.2 on the Noometry Index.

Which is cheaper, GPT-5.2 Codex or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is GPT-5.2 Codex or Inkling-Small better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 43.3 in the Noometry coding category.

Which has the bigger context window?

Inkling-Small does, with 524K tokens against 400K.

How many benchmarks do GPT-5.2 Codex and Inkling-Small share?

1 benchmark has published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper