Claude Opus 4.7 vs Claude Opus 4.8
Change modelsClaude Opus 4.7Anthropic
Claude Opus 4.8Anthropic
IndexAll categories, out of 100.
62.0 ±3.0
67.7 ±2.0 best
GapIndex points below the top.
−5.7
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
47/s
69/s best
EloLMArena rating and rank.
1483 best
1454
ReleasedMonth of release.
2026-04
2026-05
Input / 1MUS dollars per 1M input tokens.
$5.00
$5.00
Output / 1MUS dollars per 1M output tokens.
$25.00
$25.00
Batch output / 1MBatch price per 1M output tokens.
$12.50
$12.50
1K chats2K tokens in, 500 out, each.
$22.50
$22.50
1K documents20K tokens in, 1K out, each.
$125.00
$125.00
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$1,500.00
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
60.6
66.5 best
CodingCode writing and repair.
64.5
68.3 best
ReasoningLogic problems and puzzles.
61.1
68.0 best
MultimodalTasks with images and text.
61.3
66.5 best
KnowledgeFacts and expert knowledge.
61.8
66.4 best
MultilingualTasks in many languages.
—
60.3
InstructionTasks with strict prompt rules.
45.7
59.7 best
MathMath problems.
64.3
71.2 best
Benchmarks
55 sharedOnly Claude Opus 4.7: 10Only Claude Opus 4.8: 47
Claude Opus 4.7
Claude Opus 4.8