Command A+: benchmark scores, price and ranking

Command A+ from Cohere,Cohere Labs (formerly Cohere for AI) ranks #483 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.8), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Cohere,Cohere Labs (formerly Cohere for AI)
Type: Frontier model
Open weights: No
Released: 2026-05-20 (source: epoch)
Cheapest API price: $0.300 in / $1.50 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
Aggregate rank: #483 of 743 (score 46.8)

Across the 2 benchmarks where at least ten models are scored, Command A+ is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.300 per million tokens, is lower than that of 58% of the 427 models with a listed price.

Command A+ benchmark results

Command A+ benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
CritPt	0.3%	#77 of 115	Epoch AI Benchmarking Hub	2026-10-13
SciCode	37.8%	#73 of 106	Epoch AI Benchmarking Hub	2026-10-13

About Command A+

Command A+ is a frontier model from Cohere,Cohere Labs (formerly Cohere for AI). It was released on 2026-05-20, according to Epoch AI. The cheapest API listing we track charges $0.300 per million input tokens and $1.50 per million output tokens, through openrouter. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Command A+ stands

On our aggregate score, Command A+ is #483 of 743 ranked models, in the lower half. Its score is 46.8; the scale is centred on 50, so it sits 3.2 points below the typical model. That beats 35% of the ranked field. Among the 3 ranked Cohere,Cohere Labs (formerly Cohere for AI) models it is #1. The next one down is Command R+ at 45.4.

Command A+, benchmark by benchmark

Command A+ lands below the middle on CritPt: 0.3%, #77 of 115, with 66% of the field scoring higher. GPT-5.6 Sol (max) leads at 32.3%; the closest result above is Claude Sonnet 4 (unknown thinking) at 0.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so Command A+ is 2.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Command A+ lands below the middle on SciCode: 37.8%, #73 of 106, with 68% of the field scoring higher. Claude Opus 5.5 (max) leads at 66.9%; the closest result above is GLM-4.6 at 38.4%. It covers scientific research code. The board median is 44.3%, so Command A+ is 6.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Command A+ has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Command A+ costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on qwen3.6-plus ($0.325) and Qwen3-Coder-480B-A35B-Instruct ($0.380).

Release history

The Cohere,Cohere Labs (formerly Cohere for AI) model released before it was Command R+ on 2024-08-30, which scores 45.4.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#480 glm-4-9b (46.9)
#481 Llama-4-Maverick-17B-128E-Instruct (46.9)
#482 qwen3-30b-a3b-instruct-2507 (46.8)
#484 MiniMax-M2.5 (46.8)
#485 o4-mini (high) (46.8)
#486 codestral-2508 (46.8)