Noometry

Model comparison

GPT-5.5 Instant vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 47.8 to 42.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-5.5 Instant OpenAI

42.5

Rank #99 Confirmed

Kimi K2.5 Moonshot AI

47.8

Rank #50 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-5.5 Instant scores higher in 0 categories and Kimi K2.5 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.5 leads 50.3 to 26.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.1% for GPT-5.5 Instant and 92.2% for Kimi K2.5.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

GPT-5.5 InstantKimi K2.5
ProviderOpenAIMoonshot AI
Noometry Index42.547.8
Released2026-05-052026-01-27
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked2751

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

Category by category

Coding Kimi K2.5 leads

GPT-5.5 Instant: 43.7 (#73), Kimi K2.5: 48.7 (#48)

BenchmarkGPT-5.5 InstantKimi K2.5
SciCode48.6%49%
LMArena Coding14331474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
LMArena WebDev—1436
SWE-bench Multilingual—67.3%
WeirdML—45.6%
ALE-Bench—821.65

Agentic & Tool Use Not comparable

GPT-5.5 Instant: —, Kimi K2.5: 34.0 (#44)

BenchmarkGPT-5.5 InstantKimi K2.5
Terminal-Bench—43.2%
OSWorld—63.3%
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

GPT-5.5 Instant: 24.2 (#149), Kimi K2.5: 31.2 (#74)

BenchmarkGPT-5.5 InstantKimi K2.5
CritPt0%3.1%
Chess Puzzles12%12%
LMArena Hard Prompts14261454
Epoch Capabilities Index142.48148.05
ARC-AGI-2—11.8%
SimpleBench—46.8%
Kagi LLM Benchmark—78.5%
NYT Connections (extended)—69.9%
ARC-AGI-1—65.3%
EnigmaEval—3.4%
Thematic Generalization—69.4%

Math Kimi K2.5 leads

GPT-5.5 Instant: 26.1 (#241), Kimi K2.5: 50.3 (#46)

BenchmarkGPT-5.5 InstantKimi K2.5
OTIS Mock AIME 2024-202568.1%92.2%
LMArena Math14201470
FrontierMath (Tiers 1-3)26.3%—
FrontierMath Tier 42.4%—
MathArena Final-Answer Competitions—62.3%
FrontierMath (Feb 2025 set)—27.9%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Kimi K2.5 leads

GPT-5.5 Instant: 48.9 (#68), Kimi K2.5: 53.6 (#52)

BenchmarkGPT-5.5 InstantKimi K2.5
GPQA Diamond82.5%87.6%
LMArena Expert14091466
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%
Vectara Hallucination Rate—14.2%

Multimodal Kimi K2.5 leads

GPT-5.5 Instant: 39.3 (#48), Kimi K2.5: 40.4 (#37)

BenchmarkGPT-5.5 InstantKimi K2.5
LMArena Vision12501269
LMArena Document14031430

Multilingual Kimi K2.5 leads

GPT-5.5 Instant: 53.0 (#76), Kimi K2.5: 54.1 (#50)

BenchmarkGPT-5.5 InstantKimi K2.5
LMArena Non-English14171433
LMArena Chinese14571495
LMArena French14281454
LMArena German14101441
LMArena Japanese14081422
LMArena Korean13931412
LMArena Russian14301436
LMArena Spanish14301450

Instruction Following Kimi K2.5 leads

GPT-5.5 Instant: 74.4 (#94), Kimi K2.5: 75.5 (#60)

BenchmarkGPT-5.5 InstantKimi K2.5
LMArena Instruction Following14071431

Long Context Kimi K2.5 leads

GPT-5.5 Instant: 43.4 (#92), Kimi K2.5: 52.1 (#7)

BenchmarkGPT-5.5 InstantKimi K2.5
LMArena Longer Query14221445
Fiction.LiveBench—86.1%
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Kimi K2.5 leads

GPT-5.5 Instant: 62.0 (#81), Kimi K2.5: 65.3 (#51)

BenchmarkGPT-5.5 InstantKimi K2.5
LMArena Text14191445
LMArena Creative Writing14201423
LMArena Multi-Turn14341444
EQ-Bench Creative Writing—1579

Frequently asked questions

Is GPT-5.5 Instant better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 42.5 on the Noometry Index.

Is GPT-5.5 Instant or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 43.7 in the Noometry coding category.

How many benchmarks do GPT-5.5 Instant and Kimi K2.5 share?

25 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper