GPT-6.1 Sol vs GPT-6 Astra

Change models
IndexAll categories, out of 100.
78.0 ±2.2
78.0 ±1.9
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
100%
100%
SpeedOutput tokens per second.
34/s
34/s
EloLMArena rating and rank.
1446 best
1440
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00 best
$10.00
Output / 1MUS dollars per 1M output tokens.
$10.00 best
$50.00
Batch output / 1MBatch price per 1M output tokens.
$5.00 best
$25.00
1K chats2K tokens in, 500 out, each.
$9.00 best
$45.00
1K documents20K tokens in, 1K out, each.
$50.00 best
$250.00
1K agent tasks200K tokens in, 20K out, each.
$600.00 best
$3,000.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
76.0 best
74.6
CodingCode writing and repair.
75.8
76.9 best
ReasoningLogic problems and puzzles.
81.8
83.8 best
MultimodalTasks with images and text.
72.2 best
71.2
KnowledgeFacts and expert knowledge.
78.0
78.5 best
MultilingualTasks in many languages.
73.2
73.6 best
InstructionTasks with strict prompt rules.
76.6
79.5 best
MathMath problems.
78.2 best
78.0

Benchmarks

95 shared
Only GPT-6.1 Sol: 3Only GPT-6 Astra: 43
GPT-6.1 Sol
GPT-6 Astra
52.9%10 / 222
54.7% best8 / 222
83.0% best18 / 217
80.7%37 / 217
95.4%5 / 217
95.8% best3 / 217
31.7%4 / 214
31.7%4 / 214
EuroEval PolishMultilingual
66.9%3 / 209
67.4% best2 / 209
100.0%1 / 200
100.0%1 / 200
EuroEval SwedishMultilingual
77.5%2 / 195
77.6% best1 / 195
EuroEval GermanMultilingual
67.1%3 / 191
68.0% best1 / 191
74.8% best1 / 182
74.7%2 / 182
EuroEval FrenchMultilingual
76.1%3 / 178
76.3% best2 / 178
EuroEval SpanishMultilingual
68.2%3 / 176
70.0% best1 / 176
EuroEval DutchMultilingual
74.0%2 / 175
74.7% best1 / 175
EuroEval ItalianMultilingual
78.5% best1 / 174
77.8%2 / 174
61.8% best5 / 164
61.6%6 / 164
54.8% best22 / 133
53.7%25 / 133
94.2%2 / 131
95.0% best1 / 131
96.5%11 / 126
97.5% best5 / 126
88.9%10 / 123
89.6% best8 / 123
97.1%6 / 122
97.5% best5 / 122
98.5% best6 / 116
97.8%14 / 116