Skip to main content

Model profile

Command A+

CohereCurrentReleased May 20, 2026
Data verified
Overall Score
47.51Public #135 of 200
Arena Elo
Not listed
Eligible category ranks
3of 8
Price (1M tokens)
$2.5 in / $10 out
API pricing
Speed
272tok/s
Context
128K

Evidence coverage

21 of 323 tracked benchmarks are published. 4 are verified and 17 provisional. 6 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
21 / 323
Verified
4
Provisional
17
Categories with evidence
6 / 8

Evidence by category

  • Agentic5 benchmarks
    Mixed evidence
  • Coding2 benchmarks
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge7 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal4 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostReasoning
Confidence:
Low
plus

Command A+ ranks #135 out of 200 models on the public leaderboard with an overall score of 47.51/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Command A+ is a open weight model with a 128K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 21 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#27), while its weakest is Coding (#113). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 47.247.74

  1. Claude 3.5 Sonnet
    Anthropic
    #13247.74
    Claude 3.5 Sonnet is #132 with a score of 47.74.
    Compare
  2. GLM-4.5-Air
    Z.AI
    #13347.7
    GLM-4.5-Air is #133 with a score of 47.7.
    Compare
  3. Qwen3.5 Flash
    Alibaba
    #13447.65
    Qwen3.5 Flash is #134 with a score of 47.65.
    Compare
  4. Command A+Current model
    Cohere
    #13547.51
    Command A+ is #135 with a score of 47.51.
  5. o3-mini
    OpenAI
    #13647.41
    o3-mini is #136 with a score of 47.41.
    Compare
  6. Gemma 4 12B
    Google
    #13747.29
    Gemma 4 12B is #137 with a score of 47.29.
    Compare
  7. Qwen3.5 Plus
    Alibaba
    #13847.2
    Qwen3.5 Plus is #138 with a score of 47.2.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Multimodal7%
    Eligible cohort rank #27 of 29Category score 7.0
  2. Agentic31%
    Eligible cohort rank #83 of 119Category score 43.8
  3. Coding7%
    Eligible cohort rank #113 of 122Category score 35.4

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #83 of 119Percentile 31stWeight 22%5 benchmarksMixed sources43.8
CodingRank #113 of 122Percentile 7thWeight 20%2 benchmarksReported35.4
ReasoningWeight 17%2 benchmarksReportedScore pending
KnowledgeWeight 12%7 benchmarksReportedScore pending
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank #27 of 29Percentile 7thWeight 12%4 benchmarksMixed sources7.0
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic5 benchmarks
τ²-bench resultsProvider exact

τ²-Bench Tool-Agent-User Evaluation

80.7%Display only
Source: Cohere: Introducing Command A+Provenance: Cohere reports Command A+ at 85% on tau2-Bench Telecom in the launch post. BenchLM stores this on the existing Tau2-Telecom key.
AA Agentic IndexReported

Artificial Analysis Agentic Index

9.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

10.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
714Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
25%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding2 benchmarks
AA Coding IndexReported

Artificial Analysis Coding Index

27.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

37.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

46.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge7 benchmarks
Artificial Analysis Intelligence IndexSecondary exact
22.5%Display only
Source: Artificial Analysis: Command A+Provenance: Artificial Analysis reports Command A+ at 37 on the Intelligence Index.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

76.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

11.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-4.0%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

8.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

14.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA Openness IndexReported

Artificial Analysis Openness Index

38.9%Display only
Source: Artificial Analysis: artificial-analysis-openness-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multimodal4 benchmarks
MMMU-ProProvider exact

Massive Multi-discipline Multimodal Understanding Pro

63%Weighted 45%
Source: Cohere: Introducing Command A+Provenance: Cohere reports Command A+ at 63% on MMMU Pro in the launch post.
CharXivProvider exact

CharXiv Reasoning

52.7%Weighted 25%
Source: Cohere: Introducing Command A+Provenance: Cohere reports Command A+ at 52.7% on CharXiv reasoning in the launch post.
MMMUProvider exact

Massive Multi-discipline Multimodal Understanding

75.1%Display only
Source: Cohere: Introducing Command A+Provenance: Cohere reports Command A+ at 75.1% on MMMU in the launch post.
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

63.2%Display only
Source: Artificial Analysis: mmmu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

73.9%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does Command A+ perform overall in AI benchmarks?

Command A+ has 21 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Command A+ good for knowledge and understanding?

Command A+ has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Command A+ good for coding and programming?

Command A+ ranks #113 out of 122 models in coding and programming benchmarks with an average score of 35.4. There are stronger options in this category.

Is Command A+ good for reasoning and logic?

Command A+ has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Command A+ good for agentic tool use and computer tasks?

Command A+ ranks #83 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 43.8. There are stronger options in this category.

Is Command A+ good for multimodal and grounded tasks?

Command A+ ranks #27 out of 29 models in multimodal and grounded tasks benchmarks with an average score of 7. There are stronger options in this category.

Is Command A+ good for instruction following?

Command A+ has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is Command A+ open source?

Yes, Command A+ is an open weight model created by Cohere, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Command A+ have full benchmark coverage on BenchLM?

Not yet. Command A+ currently has 21 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Command A+?

Command A+ has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.