Claude Opus 5.5 vs GPT-6 Astra

Change models
IndexAll categories, out of 100.
78.6 ±2.4 best
78.0 ±1.9
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
76/s best
34/s
EloLMArena rating and rank.
1513 best
1440
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$4.00 best
$10.00
Output / 1MUS dollars per 1M output tokens.
$20.00 best
$50.00
Batch output / 1MBatch price per 1M output tokens.
$10.00 best
$25.00
1K chats2K tokens in, 500 out, each.
$18.00 best
$45.00
1K documents20K tokens in, 1K out, each.
$100.00 best
$250.00
1K agent tasks200K tokens in, 20K out, each.
$1,200.00 best
$3,000.00
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
74.1
74.6 best
CodingCode writing and repair.
81.8 best
76.9
ReasoningLogic problems and puzzles.
80.8
83.8 best
MultimodalTasks with images and text.
74.1 best
71.2
KnowledgeFacts and expert knowledge.
79.2 best
78.5
MultilingualTasks in many languages.
—
73.6
InstructionTasks with strict prompt rules.
59.6
79.5 best
MathMath problems.
77.7
78.0 best

Benchmarks

114 shared
Only Claude Opus 5.5: 43Only GPT-6 Astra: 24
Claude Opus 5.5
GPT-6 Astra
61.4% best2 / 222
54.7%8 / 222
84.7% best6 / 217
80.7%37 / 217
90.6%38 / 217
95.8% best3 / 217
31.7%4 / 214
31.7%4 / 214
100.0%1 / 200
100.0%1 / 200
65.5% best3 / 164
61.6%6 / 164
68.3% best1 / 133
53.7%25 / 133
91.7%6 / 131
95.0% best1 / 131
97.5%5 / 126
97.5%5 / 126
90.3% best6 / 123
89.6%8 / 123
97.9% best3 / 122
97.5%5 / 122
98.3% best8 / 116
97.8%14 / 116
66.9% best2 / 114
56.5%24 / 114
87.7% best1 / 113
86.9%2 / 113
MedScribeHealthcare
91.4% best1 / 109
87.9%16 / 109
MedCodeHealthcare
49.8% best19 / 106
48.5%29 / 106
72.2%7 / 91
75.6% best4 / 91
Chess PuzzlesReasoning
67.0%5 / 90
74.0% best3 / 90
91.2%4 / 90
93.7% best2 / 90
50.5% best7 / 90
39.4%37 / 90