Noometry

Model comparison

GPT-4 Turbo vs Kimi K2.7 Code

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 30.5 on the Noometry Index.

Last verified . 7 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 7 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Kimi K2.7 Code in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 95.6% for Kimi K2.7 Code.
  • Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Kimi K2.7 Code accepts more context: 262K tokens versus 128K.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboKimi K2.7 Code
ProviderOpenAIMoonshot AI
Noometry Index30.543.3
Released2023-11-062026-06-12
WeightsProprietaryOpen
Context window128K262K
Max output4K262K
Input $ / M tokens$10$0.95
Output $ / M tokens$30$4
Results tracked3619

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

Category by category

Coding Kimi K2.7 Code leads

GPT-4 Turbo: 33.8 (#249), Kimi K2.7 Code: 42.9 (#95)

BenchmarkGPT-4 TurboKimi K2.7 Code
WeirdML18%54.1%
DeepSWE—30.5%
FrontierCode—30.1%
LMArena WebDev—1473
SciCode—47.5%
BigCodeBench Instruct48.2%—
LMArena Coding1268—
BigCodeBench Complete58.2%—
ALE-Bench—886.23
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Kimi K2.7 Code: 24.0 (#122)

BenchmarkGPT-4 TurboKimi K2.7 Code
APEX-Agents—37.6%
GBAEval—0.9%
METR Time Horizons36.7%—
Vending-Bench 2—5,083

Reasoning Kimi K2.7 Code leads

GPT-4 Turbo: 15.3 (#317), Kimi K2.7 Code: 39.0 (#61)

BenchmarkGPT-4 TurboKimi K2.7 Code
SimpleBench25.1%57.9%
Chess Puzzles6%21%
Epoch Capabilities Index127.25149.97
CritPt—10%
LMArena Hard Prompts1251—
DTBench61.6%—
LMCA9.8%—
Surface Evolver Bench—48.8%
ForecastBench59.4—

Math Kimi K2.7 Code leads

GPT-4 Turbo: 9.0 (#322), Kimi K2.7 Code: 52.9 (#48)

BenchmarkGPT-4 TurboKimi K2.7 Code
FrontierMath (Tiers 1-3)0.7%54%
OTIS Mock AIME 2024-20256.7%95.6%
FrontierMath Tier 4—12.2%
LMArena Math1272—
MATH Level 546.7%—

Knowledge Kimi K2.7 Code leads

GPT-4 Turbo: 24.3 (#268), Kimi K2.7 Code: 53.5 (#57)

BenchmarkGPT-4 TurboKimi K2.7 Code
GPQA Diamond46.6%87.9%
SimpleQA Verified—36.5%
Confabulations28.4%—
LMArena Expert1223—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Kimi K2.7 Code: —

BenchmarkGPT-4 TurboKimi K2.7 Code
LMArena Vision1090—

Multilingual Not comparable

GPT-4 Turbo: 40.5 (#216), Kimi K2.7 Code: —

BenchmarkGPT-4 TurboKimi K2.7 Code
LMArena Non-English1245—
LMArena Chinese1242—
LMArena French1276—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following Not comparable

GPT-4 Turbo: 65.8 (#216), Kimi K2.7 Code: —

BenchmarkGPT-4 TurboKimi K2.7 Code
LMArena Instruction Following1249—

Long Context Not comparable

GPT-4 Turbo: 38.0 (#206), Kimi K2.7 Code: —

BenchmarkGPT-4 TurboKimi K2.7 Code
LMArena Longer Query1254—

Writing & Preference Not comparable

GPT-4 Turbo: 47.7 (#206), Kimi K2.7 Code: —

BenchmarkGPT-4 TurboKimi K2.7 Code
LMArena Text1272—
LMArena Creative Writing1269—
LMArena Multi-Turn1267—

Frequently asked questions

Is GPT-4 Turbo better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Kimi K2.7 Code does, with 262K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Kimi K2.7 Code share?

7 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper