GPT-5.5 vs GPT-6 Astra

Change models
GPT-5.5OpenAI
IndexAll categories, out of 100.
69.1 ±2.5
78.0 ±1.9 best
GapIndex points below the top.
−8.9
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
52/s best
34/s
EloLMArena rating and rank.
1466 best
1440
ReleasedMonth of release.
2026-04
2026-09
Input / 1MUS dollars per 1M input tokens.
$5.00 best
$10.00
Output / 1MUS dollars per 1M output tokens.
$30.00 best
$50.00
Batch output / 1MBatch price per 1M output tokens.
$15.00 best
$25.00
1K chats2K tokens in, 500 out, each.
$25.00 best
$45.00
1K documents20K tokens in, 1K out, each.
$130.00 best
$250.00
1K agent tasks200K tokens in, 20K out, each.
$1,600.00 best
$3,000.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.8
74.6 best
CodingCode writing and repair.
65.5
76.9 best
ReasoningLogic problems and puzzles.
74.1
83.8 best
MultimodalTasks with images and text.
66.8
71.2 best
KnowledgeFacts and expert knowledge.
70.4
78.5 best
MultilingualTasks in many languages.
—
73.6
InstructionTasks with strict prompt rules.
64.8
79.5 best
MathMath problems.
74.7
78.0 best

Benchmarks

66 shared
Only GPT-5.5: 46Only GPT-6 Astra: 72
GPT-5.5
GPT-6 Astra
45.8%26 / 222
54.7% best8 / 222
84.3% best7 / 217
80.7%37 / 217
94.0%13 / 217
95.8% best3 / 217
27.1%17 / 214
31.7% best4 / 214
100.0%1 / 200
100.0%1 / 200
93.5%8 / 199
96.1% best1 / 199
58.0%10 / 164
61.6% best6 / 164
93.6%8 / 141
96.0% best1 / 141
42.5%44 / 133
53.7% best25 / 133
85.0%13 / 131
95.0% best1 / 131
95.0%19 / 126
97.5% best5 / 126
69.8%50 / 123
89.6% best8 / 123
90.6%14 / 122
97.5% best5 / 122
97.5%19 / 116
97.8% best14 / 116
55.8%27 / 114
56.5% best24 / 114
79.9%23 / 113
86.9% best2 / 113
MedScribeHealthcare
86.9%19 / 109
87.9% best16 / 109
MedCodeHealthcare
49.1% best26 / 106
48.5%29 / 106
63.0%16 / 91
75.6% best4 / 91
Chess PuzzlesReasoning
63.0%7 / 90
74.0% best3 / 90