Claude Fable 5.1 vs GPT-6.2 Astra

Change models
IndexAll categories, out of 100.
74.5 ±2.5
79.5 ±3.1 best
GapIndex points below the top.
−5.0
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
68/s best
39/s
EloLMArena rating and rank.
1512 best
1414
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$10.00
$8.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$40.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
$20.00 best
1K chats2K tokens in, 500 out, each.
$45.00
$36.00 best
1K documents20K tokens in, 1K out, each.
$250.00
$200.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$2,400.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
69.1
74.7 best
CodingCode writing and repair.
76.2
79.4 best
ReasoningLogic problems and puzzles.
75.5
86.2 best
MultimodalTasks with images and text.
73.2 best
70.7
KnowledgeFacts and expert knowledge.
76.0
79.9 best
MultilingualTasks in many languages.
—
74.0
InstructionTasks with strict prompt rules.
72.8
—
MathMath problems.
75.4
76.4 best

Benchmarks

37 shared
Only Claude Fable 5.1: 92Only GPT-6.2 Astra: 26
Claude Fable 5.1
GPT-6.2 Astra
100.0%1 / 203
100.0%1 / 203
68.4%3 / 170
68.6% best2 / 170
90.0%11 / 137
95.8% best1 / 137
97.5%7 / 132
98.5% best1 / 132
90.3% best7 / 130
89.9%9 / 130
98.3% best2 / 127
97.5%6 / 127
99.0%3 / 116
99.3% best2 / 116
55.3% best3 / 98
42.8%31 / 98
70.8%11 / 94
78.5% best2 / 94
Chess PuzzlesReasoning
48.0%22 / 93
78.0% best3 / 93
90.2%9 / 93
92.6% best4 / 93
50.7% best4 / 89
21.8%54 / 89
58.0%13 / 83
95.0% best1 / 83
87.8%11 / 75
100.0% best1 / 75
58.1%9 / 68
63.1% best4 / 68
13.59 / 59
14.0 best7 / 59
14.2 best8 / 59
12.410 / 59
10.0%15 / 55
17.0% best4 / 55
57.3%11 / 52
62.1% best6 / 52
40.0%10 / 48
71.4% best1 / 48