Qwen3.8-Flash-Next vs Sakana Fugu
Change modelsQwen3.8-Flash-NextAlibaba
Sakana FuguSakana
IndexAll categories, out of 100.
63.0 ±3.3 best
62.9 ±7.7
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
74/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-06
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
262K
1M best
AgenticMulti-step tasks with tools.
66.8
66.8
CodingCode writing and repair.
61.1
63.4 best
ReasoningLogic problems and puzzles.
61.2
63.0 best
MultimodalTasks with images and text.
63.4 best
60.1
KnowledgeFacts and expert knowledge.
55.1
67.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
72.2
—
MathMath problems.
58.6
—
Benchmarks
6 sharedOnly Qwen3.8-Flash-Next: 43Only Sakana Fugu: 4
Qwen3.8-Flash-Next
Sakana Fugu