Claude Fable 5 vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
73.5 ±2.7 best
72.0 ±8.0
GapIndex points below the top.
Top
−1.5 · no clear gap
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
40/s
40/s
EloLMArena rating and rank.
1492
—
ReleasedMonth of release.
2026-06
2026-11
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$5.25 best
1K documents20K tokens in, 1K out, each.
$250.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$390.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
70.9
75.2 best
CodingCode writing and repair.
74.1 best
67.0
ReasoningLogic problems and puzzles.
73.2
—
MultimodalTasks with images and text.
69.7
72.1 best
KnowledgeFacts and expert knowledge.
75.4 best
70.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.8
—
MathMath problems.
75.8
—

Benchmarks

8 shared
Only Claude Fable 5: 84Only Qwen4 Max: 11
Claude Fable 5
Qwen4 Max
65.4% best4 / 167
43.7%42 / 167
90.4% best4 / 125
86.7%14 / 125
49.5% best10 / 92
41.3%31 / 92
38.3%14 / 84
40.4% best12 / 84
41.4%16 / 63
48.5% best14 / 63
6.217 / 56
8.4 best15 / 56
48.8% best12 / 26
46.3%15 / 26
51.1%
48.5%