Qwen3.8 Flash Next — Benchmarks

Benchmark scores for Qwen3.8 Flash Next aggregated from public leaderboards (4 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

No llmrun Composite Score for Qwen3.8 Flash Next: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board — or on 3 boards that narrow its score to a 90% range of at most 15.6 points. Either way the results must come from at least two different benchmarks. Its individual scores below stand on their own — see how the llmrun Composite Score gets calculated.

Qwen3.8 Flash Next reasoning benchmarks

Multi-step logic and problem-solving — can the model think through a hard problem rather than recall an answer.

LiveBench Reasoning
LiveBench Reasoning measures logical, multi-step reasoning using contamination-free questions that are refreshed regularly, so models cannot have trained on the test set.
87.4
87.4
median 82.7open leader 90.7
Overall best: GPT 6 Astra Max 92.7
94th percentile · #2 of 19 open · #28 of 70 all
#2 of 19
#28 of 70
Independent
LiveBench · Jun 2026

Qwen3.8 Flash Next coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

LiveBench Coding
LiveBench Coding evaluates code generation and completion on fresh, contamination-free programming tasks that are updated regularly.
72.5
72.5
median 75.0open leader 81.5
Overall best: Claude Sonnet 5.5 Max 91.4
39th percentile · #12 of 19 open · #57 of 70 all
#12 of 19
#57 of 70
Independent
LiveBench · Jun 2026

Other results (1)· leaderboard-only, not part of the llmrun Score

LMArena WebDev
Code Arena (formerly WebDev Arena) is Arena's head-to-head coding leaderboard: two models each build a real web app or UI from the same prompt, and people vote blind on which result is better. The rating shown is a relative Bradley-Terry score, not a percentage — compare it only to other models on this board.
1630.3
1630.3
median 1411.4open leader 1655.2
Overall best: Claude Opus 5.5 (Max) 1807.3
94th percentile · #4 of 52 open · #19 of 138 all
#4 of 52
#19 of 138
Arena
Arena · Oct 2026

Qwen3.8 Flash Next math benchmarks

Symbolic and quantitative problem-solving, from competition math to multi-step calculation.

LiveBench Math
LiveBench Math measures mathematical problem-solving on contamination-free, regularly-refreshed questions, including competition-style problems.
85.8
85.8
median 86.8open leader 95.1
Overall best: Claude Opus 5.5 Max 97.1
39th percentile · #12 of 19 open · #55 of 70 all
#12 of 19
#55 of 70
Independent
LiveBench · Jun 2026

Scores aggregated from public benchmark sources (LiveBench: 3 boards, Arena: 1 board) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.