Qwen3.8 Max (0902) vs Claude Opus 4.7

Change models
IndexAll categories, out of 100.
62.6 ±7.1 best
61.8 ±2.9
GapIndex points below the top.
Top
−0.8 · no clear gap
CoverageIndex weight that has results.
80%
95% best
SpeedOutput tokens per second.
32/s
47/s best
EloLMArena rating and rank.
—
1483
ReleasedMonth of release.
2026-09
2026-04
Input / 1MUS dollars per 1M input tokens.
$2.00 best
$5.00
Output / 1MUS dollars per 1M output tokens.
$6.00 best
$25.00
Batch output / 1MBatch price per 1M output tokens.
$3.45 best
$12.50
1K chats2K tokens in, 500 out, each.
$7.00 best
$22.50
1K documents20K tokens in, 1K out, each.
$46.00 best
$125.00
1K agent tasks200K tokens in, 20K out, each.
$520.00 best
$1,500.00
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
66.1 best
60.3
CodingCode writing and repair.
66.8 best
64.3
ReasoningLogic problems and puzzles.
58.7
60.8 best
MultimodalTasks with images and text.
—
61.1
KnowledgeFacts and expert knowledge.
62.2 best
61.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
45.6
MathMath problems.
64.5 best
64.0

Benchmarks

8 shared
Only Qwen3.8 Max (0902): 2Only Claude Opus 4.7: 59
Qwen3.8 Max (0902)
Claude Opus 4.7
92.3% best28 / 217
86.4%67 / 217
100.0% best1 / 200
86.7%69 / 200
47.3%36 / 91
51.7% best28 / 91
Chess PuzzlesReasoning
37.0%39 / 90
41.0% best34 / 90
65.6%37 / 90
70.2% best29 / 90
34.1% best30 / 72
31.7%32 / 72
47.8% best19 / 39
43.3%21 / 39
20.0%37 / 37
33.3% best26 / 37