Noometry

Model comparison

Command R+ vs GPT-6 Astra

GPT-6 Astra is the stronger model overall, scoring 70.8 to 32.4 on the Noometry Index. Command R+ costs 4.6× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and GPT-6 Astra in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 9.2.
  • The biggest single-benchmark swing is LMCA: 5% for Command R+ and 64.4% for GPT-6 Astra.
  • Command R+ is cheaper at $2.50 / $10 per million input/output tokens, against $10 / $50 for GPT-6 Astra.
  • GPT-6 Astra accepts more context: 1.05M tokens versus 128K.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Command R+GPT-6 Astra
ProviderCohereOpenAI
Noometry Index32.470.8
Released2024-08-302026-09-03
WeightsOpenProprietary
Context window128K1.05M
Max output4K128K
Input $ / M tokens$2.50$10
Output $ / M tokens$10$50
Results tracked3456

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

Category by category

Coding GPT-6 Astra leads

Command R+: 29.1 (#309), GPT-6 Astra: 73.7 (#2)

BenchmarkCommand R+GPT-6 Astra
LMArena Coding11871487
DeepSWE—74.1%
FrontierCode—53.3%
LMArena WebDev—1786
FrontierSWE—65.5%
SciCode—56.5%
GSO—79.4%
WeirdML—93.6%
BigCodeBench Instruct33.8%—
LiveBench Coding19.1%—
MirrorCode—46.7%
BigCodeBench Complete41.9%—
ALE-Bench—2,951
HumanEval+56.7%—
MBPP+63.5%—

Agentic & Tool Use Not comparable

Command R+: —, GPT-6 Astra: 52.9 (#3)

BenchmarkCommand R+GPT-6 Astra
APEX-Agents—64.7%
Remote Labor Index—20.8%
BALROG—68.3%
GDP.pdf—34.2%
Vending-Bench 2—15,515

Reasoning GPT-6 Astra leads

Command R+: 9.2 (#344), GPT-6 Astra: 85.1 (#1)

BenchmarkCommand R+GPT-6 Astra
LMArena Hard Prompts11861462
DTBench54.9%97.3%
LMCA5%64.4%
Epoch Capabilities Index119.34166.45
ARC-AGI-2—95%
SimpleBench17.4%—
NYT Connections (extended)—98.1%
ARC-AGI-1—98.5%
CritPt—31.7%
Chess Puzzles—72%
EBR-Bench—76.2%
LiveBench Reasoning24.8%—
Mystery Game Puzzles—84%
LiveBench Data Analysis38.1%—
Bench to the Future 3—0.14
LiveBench31.8%—

Math GPT-6 Astra leads

Command R+: 28.9 (#242), GPT-6 Astra: 93.5 (#2)

BenchmarkCommand R+GPT-6 Astra
LMArena Math11881465
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—97.6%
OTIS Mock AIME 2024-2025—100%
ProofBench—99%
LiveBench Math21.3%—
FrontierMath Erdős—2.9%

Knowledge GPT-6 Astra leads

Command R+: 36.4 (#169), GPT-6 Astra: 75.3 (#1)

BenchmarkCommand R+GPT-6 Astra
Vectara Hallucination Rate6.9%8.7%
LMArena Expert11741483
GPQA Diamond—95.8%
Humanity's Last Exam—54.8%
SimpleQA Verified—75.6%
MMLU69.4%—

Multimodal Not comparable

Command R+: —, GPT-6 Astra: 55.0 (#3)

BenchmarkCommand R+GPT-6 Astra
LMArena Vision—1281
Blueprint-Bench 2—49.7%
Furniture Assembly—80%
LMArena Document—1468

Multilingual GPT-6 Astra leads

Command R+: 38.6 (#227), GPT-6 Astra: 53.7 (#61)

BenchmarkCommand R+GPT-6 Astra
LMArena Non-English12161430
LMArena Chinese12261484
LMArena French12091456
LMArena German12161440
LMArena Japanese11661379
LMArena Korean11381426
LMArena Russian12271436
LMArena Spanish11891407

Instruction Following GPT-6 Astra leads

Command R+: 60.0 (#254), GPT-6 Astra: 76.3 (#44)

BenchmarkCommand R+GPT-6 Astra
LMArena Instruction Following11971450
LiveBench Instruction Following57.6%—

Long Context GPT-6 Astra leads

Command R+: 37.3 (#219), GPT-6 Astra: 44.5 (#62)

BenchmarkCommand R+GPT-6 Astra
LMArena Longer Query12301456

Writing & Preference GPT-6 Astra leads

Command R+: 43.5 (#228), GPT-6 Astra: 75.3 (#7)

BenchmarkCommand R+GPT-6 Astra
LMArena Text12291441
LMArena Creative Writing12351418
LMArena Multi-Turn12131448
EQ-Bench Creative Writing—2173
LiveBench Language29.7%—

Frequently asked questions

Is Command R+ better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 32.4 on the Noometry Index. Command R+ costs 4.6× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.

Which is cheaper, Command R+ or GPT-6 Astra?

Command R+ is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-6 Astra lists at $10 and $50.

Is Command R+ or GPT-6 Astra better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 29.1 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Astra does, with 1.05M tokens against 128K.

How many benchmarks do Command R+ and GPT-6 Astra share?

21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-6 Astra has 56.

Related comparisons

Go deeper