Noometry

Model comparison

Command A vs GPT-4 Turbo

Command A is the stronger model overall, scoring 36.5 to 30.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

Command A Cohere

36.5

Rank #215 Confirmed

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Command A scores higher in 6 categories and GPT-4 Turbo in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Command A leads 36.2 to 9.0.
  • Command A is cheaper at $2.50 / $10 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Command A accepts more context: 256K tokens versus 128K.
  • Command A has downloadable open weights; the other is API-only.

Side by side

Command AGPT-4 Turbo
ProviderCohereOpenAI
Noometry Index36.530.5
Released2025-03-132023-11-06
WeightsOpenProprietary
Context window256K128K
Max output8K4K
Input $ / M tokens$2.50$10
Output $ / M tokens$10$30
Results tracked2436

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

Category by category

Coding GPT-4 Turbo leads

Command A: 27.2 (#322), GPT-4 Turbo: 33.8 (#249)

BenchmarkCommand AGPT-4 Turbo
LMArena Coding13301268
Aider Polyglot12%—
WeirdML—18%
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), GPT-4 Turbo: —

BenchmarkCommand AGPT-4 Turbo
Berkeley Function Calling Leaderboard57.1%—
METR Time Horizons—36.7%

Reasoning Command A leads

Command A: 18.3 (#283), GPT-4 Turbo: 15.3 (#317)

BenchmarkCommand AGPT-4 Turbo
LMArena Hard Prompts13261251
DTBench61.3%61.6%
LMCA10.3%9.8%
SimpleBench—25.1%
Kagi LLM Benchmark28.8%—
Chess Puzzles—6%
Epoch Capabilities Index—127.25
ForecastBench—59.4

Math Command A leads

Command A: 36.2 (#171), GPT-4 Turbo: 9.0 (#322)

BenchmarkCommand AGPT-4 Turbo
LMArena Math13001272
FrontierMath (Tiers 1-3)—0.7%
OTIS Mock AIME 2024-2025—6.7%
MATH Level 5—46.7%

Knowledge Command A leads

Command A: 37.1 (#159), GPT-4 Turbo: 24.3 (#268)

BenchmarkCommand AGPT-4 Turbo
LMArena Expert12951223
GPQA Diamond—46.6%
Confabulations—28.4%
Vectara Hallucination Rate9.3%—
MMLU—81.3%

Multimodal Not comparable

Command A: —, GPT-4 Turbo: 30.6 (#110)

BenchmarkCommand AGPT-4 Turbo
LMArena Vision—1090

Multilingual Command A leads

Command A: 45.3 (#170), GPT-4 Turbo: 40.5 (#216)

BenchmarkCommand AGPT-4 Turbo
LMArena Non-English13131245
LMArena Chinese13271242
LMArena French13511276
LMArena German13411259
LMArena Japanese12851194
LMArena Korean12851187
LMArena Russian13141259
LMArena Spanish13471260

Instruction Following Command A leads

Command A: 69.1 (#177), GPT-4 Turbo: 65.8 (#216)

BenchmarkCommand AGPT-4 Turbo
LMArena Instruction Following13091249

Long Context Command A leads

Command A: 40.6 (#151), GPT-4 Turbo: 38.0 (#206)

BenchmarkCommand AGPT-4 Turbo
LMArena Longer Query13341254

Writing & Preference Too close to call

Command A: 47.6 (#208), GPT-4 Turbo: 47.7 (#206)

BenchmarkCommand AGPT-4 Turbo
LMArena Text13311272
LMArena Creative Writing13191269
LMArena Multi-Turn13391267
EQ-Bench Creative Writing1145—

Frequently asked questions

Is Command A better than GPT-4 Turbo?

Command A is the stronger model overall, scoring 36.5 to 30.5 on the Noometry Index.

Which is cheaper, Command A or GPT-4 Turbo?

Command A is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is Command A or GPT-4 Turbo better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Command A does, with 256K tokens against 128K.

How many benchmarks do Command A and GPT-4 Turbo share?

19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper