Command A+
- Input
- $0.30/M tok
- Output
- $1.50/M tok
- Blended
- $0.60/M tok · 3:1
- Speed
- 152tok/s
- Context
- 192Ktokens
- Cost per task
- ~$0.63/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Command A+. Price = AA median host price.
Rankings
Coding
Verified#105 / 137rank by quality31.0±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#75 / 162rank by quality49.3±9.5quality / 1001/5 benchmarks measuredVision
Verified#74 / 98rank by quality33.2±6.3quality / 1002/6 benchmarks measuredHard reasoning
Verified#125 / 218rank by quality36.6±3.7quality / 1003/4 benchmarks measuredAgents
Verified#106 / 187rank by quality27.8±4.3quality / 1004/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 4× H200 141GB
- FP8 weights
- Throughput
- ~9,822 tok/s
- many requests batched
- Price
- $0.19–1.56 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Ultra 512GB (int4, ~67 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (218B params, 25B active per token) + 25% KV-cache headroom ≈ 273 GB
- 4× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~9,822 output tok/s aggregate at batch 353 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~74,806 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#17 of 21 (estimated)~69.5%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #16Nemotron 3 Ultra70.7%
- ~#17Command A+Estimated69.5%
- #17Intern-S2-Preview (35B-A3B)64.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~48.1%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Command A+Estimated48.1%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#40 of 46 (estimated)~43.1%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #39Beam 1.0 501B A23B43.3%
- ~#40Command A+Estimated43.1%
- #40Qwen3.8 27B42.2%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#17 of 28 (estimated)~59.5%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #16Claude Haiku 4.561.5%
- ~#17Command A+Estimated59.5%
- #17GLM-5.3 NVFP453.5%
No published score — estimated from related benchmarks
SciCodeVerified
#88 of 11838.5%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #86North Mini Code38.8%
- #88Command A+38.5%
- #88Mercury 2.538.5%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~28.7
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Command A+Estimated28.7
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#27 of 13973.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #26Ternary Bonsai 2 27B74.0%
- #27Command A+73.9%
- #28GPT-5.4 mini73.3%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Estimated
~#44 of 57 (estimated)~1374 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #43Qwen3 Next 80B A3B Instruct1386
- ~#44Command A+Estimated1374
- #44GLM-4.6VFew votes1361
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#44 of 57 (estimated)~1392 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #43Qwen3 Next 80B A3B Instruct1399
- ~#44Command A+Estimated1392
- #44GLM-4.6VFew votes1378
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1475 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #21Gemini 3.1 Pro1491
- ~#22Command A+Estimated1475
- #22Mistral Large 31412
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#58 of 8763.2%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #57Nova 2.0 Lite63.8%
- #58Command A+63.2%
- #59Llama 4 Maverick62.1%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#6 of 8 (estimated)~78.7%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #5Claude Haiku 4.579.6%
- ~#6Command A+Estimated78.7%
- #6Mistral Small 476.4%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#43 of 471.0%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #41Mistral Large 31.2%
- #43Command A+1.0%
- #43Devstral Small 21.0%
artificialanalysis.ai · 2026-09-24
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
Humanity's Last ExamVerified
#98 of 19812.0%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #98Cogito v2.112.0%
- #98Command A+12.0%
- #98Nemotron Cascade 2 30B A3B12.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~69.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Command A+Estimated69.4%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#32 of 11980.7%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #30Tri-21B-Think81.0%
- #32Command A+80.7%
- #32o380.7%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~60.4%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Command A+Estimated60.4%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~56.7%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Command A+Estimated56.7%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#69 of 91500 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #68Qwen3 Coder Next501
- #69Command A+500
- #70GPT-5.5 Instant (June 2026)497
artificialanalysis.ai · 2026-09-24