Qwen3.8-Flash-Next
Qwen3.8-Flash-Next ranks first on BRIDGE.
11
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
Qwen Aug 2026 Qwen3.8-Flash-Next
Open weights
No Epoch Capabilities Index score yet
- Agent Arena -4.61% #41 /56
- Political Science LLM Benchmark 67.5% #15 /42
- GameWorld 61.5% #3 /22
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SEA-HELM | 73.0 | #23 of 71 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Code Arena | 1,624 | #26 of 128 | Official leaderboard | |
| Data Agent Benchmark | 70.9% | #11 of 18 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GameWorld | 61.5% | #3 of 22 | Official leaderboard | |
| CivBench | 1,499 | #10 of 19 | Official leaderboard | |
| Agent Arena | -4.61% | #41 of 56 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BRIDGE | 56.0 | #1 of 39 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MDPBench | 80.5 | #4 of 12 | Official leaderboard | |
| ExtractBench | 89.9% | #10 of 27 | Official leaderboard | |
| GlobeBench | 23.2% | #8 of 19 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Political Science LLM Benchmark | 67.5% | #15 of 42 | Official leaderboard |