Noometry

Model comparison

Claude Opus 4.5 vs Inkling-Small

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Inkling-Small in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Opus 4.5 leads 54.8 to 43.6.
  • The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 6% for Inkling-Small.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Inkling-Small accepts more context: 524K tokens versus 200K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5Inkling-Small
ProviderAnthropicThinking Machines Lab
Noometry Index50.546.5
Released2025-11-012026-07-15
WeightsProprietaryOpen
Context window200K524K
Max output64K1.05M
Input $ / M tokens$5$0.45
Output $ / M tokens$25$1.20
Results tracked6933

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), Inkling-Small: 43.6 (#85)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena WebDev14941409
LMArena Coding15041451
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—48.7%
GSO26.5%—
WeirdML63.7%—
ALE-Bench1,025—
AlgoTune1.77—

Agentic & Tool Use Not comparable

Claude Opus 4.5: 47.3 (#12), Inkling-Small: —

BenchmarkClaude Opus 4.5Inkling-Small
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
LMArena Search1180—
METR Time Horizons75%—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), Inkling-Small: 38.6 (#63)

BenchmarkClaude Opus 4.5Inkling-Small
ARC-AGI-237.6%40.1%
ARC-AGI-180%84%
Chess Puzzles12%18%
LMArena Hard Prompts14761423
Mystery Game Puzzles22%6%
Epoch Capabilities Index150.09150.15
SimpleBench62%—
Kagi LLM Benchmark80.2%—
NYT Connections (extended)52.5%—
CritPt—8.3%
EnigmaEval11.9%—
EBR-Bench14.3%—
DTBench89.9%—
LMCA44.5%—
ForecastBench60.7—

Math Inkling-Small leads

Claude Opus 4.5: 38.6 (#132), Inkling-Small: 45.1 (#77)

BenchmarkClaude Opus 4.5Inkling-Small
FrontierMath (Tiers 1-3)34.4%46.3%
FrontierMath Tier 44.9%17.1%
OTIS Mock AIME 2024-202586.1%90%
ProofBench36%6%
LMArena Math14631459
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), Inkling-Small: 48.2 (#77)

BenchmarkClaude Opus 4.5Inkling-Small
GPQA Diamond86%88.5%
SimpleQA Verified45.7%19.1%
LMArena Expert14871442
Humanity's Last Exam25.2%—
Vectara Hallucination Rate10.9%—

Multimodal Inkling-Small leads

Claude Opus 4.5: 31.4 (#107), Inkling-Small: 39.1 (#62)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena Vision—1235
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), Inkling-Small: 51.7 (#104)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena Non-English14381402
LMArena Chinese14701465
LMArena French14711436
LMArena German14491405
LMArena Japanese14161405
LMArena Korean14241363
LMArena Russian14471391
LMArena Spanish14581428

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Inkling-Small: 73.8 (#114)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena Instruction Following14781399

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Inkling-Small: 42.7 (#118)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena Longer Query14801401
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), Inkling-Small: 59.6 (#107)

BenchmarkClaude Opus 4.5Inkling-Small
LMArena Text14511414
LMArena Creative Writing14451331
EQ-Bench Creative Writing16871491
LMArena Multi-Turn14661418

Frequently asked questions

Is Claude Opus 4.5 better than Inkling-Small?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Inkling-Small better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 43.6 in the Noometry coding category.

Which has the bigger context window?

Inkling-Small does, with 524K tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Inkling-Small share?

30 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper