Claude 4 Sonnet vs Command A+

Change models
Command A+Cohere
IndexAll categories, out of 100.
39.7 ±5.0
40.2 ±6.0 best
GapIndex points below the top.
−0.5 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
40/s
237/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-05
2026-05
Input / 1MUS dollars per 1M input tokens.
$3.00
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$1.50 best
1K chats2K tokens in, 500 out, each.
$13.50
$1.35 best
1K documents20K tokens in, 1K out, each.
$75.00
$7.50 best
1K agent tasks200K tokens in, 20K out, each.
$900.00
$90.00 best
ContextMaximum tokens in one request.
200K best
192K
AgenticMulti-step tasks with tools.
44.8 best
41.7
CodingCode writing and repair.
51.6 best
45.5
ReasoningLogic problems and puzzles.
38.0
40.1 best
MultimodalTasks with images and text.
36.2 best
34.7
KnowledgeFacts and expert knowledge.
36.4 best
36.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
31.7
57.2 best
MathMath problems.
17.0
—

Benchmarks

8 shared
Only Claude 4 Sonnet: 9Only Command A+: 10
Claude 4 Sonnet
Command A+
4.3%184 / 216
12.0% best129 / 216
44.0%159 / 211
52.7% best145 / 211
1.1% best113 / 207
0.3%132 / 207
68.3%129 / 193
76.1% best107 / 193
22.7% best119 / 170
9.8%166 / 170
52.3%89 / 143
85.0% best54 / 143
45.4%82 / 140
73.9% best25 / 140
62.4%83 / 109
63.2% best82 / 109