EnterpriseOps-Gym-AA ↗47.36%
Qwen3.8 2.4T A95B · EnterpriseOps-Gym-AA ↗
Qwen / MODEL EVIDENCE
Qwen3.8 2.4T A95B
5 benchmarks · 5 observations · 5 sources · released 2026-08-12
Scores at a glance
5 benchmarks · large dot: Qwen3.8 2.4T A95B; small dots: closest models where reported
GPQA Diamond ↗93.54%
Qwen3.8 2.4T A95B · GPQA Diamond · AA implementation ↗
τ³-Banking ↗49.07%
Qwen3.8 2.4T A95B · τ³-Banking ↗
Terminal-Bench 2.1 ↗82.02%
Qwen3.8 2.4T A95B · Terminal-Bench 2.1 ↗
MCP Atlas ↗84.50%
Qwen3.8-2.4T-A95B (xHigh) · Scale Labs · Score ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Kimi K3 →Kimi
4 of 5 shared benchmark comparisons
Qwen3.8 Max →Qwen
3 of 5 shared benchmark comparisons
Muse Spark 1.3 →Meta
3 of 5 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
POST-TRAINING / SOURCE DISCLOSURE
What the Qwen3.8 Max / 2.4T-A95B report says
The official model card identifies 2.4T-A95B as post-trained and distinguishes its open weights from the Max service, which adds features. It documents the release and architecture without a reproducible optimization recipe.
- Post-trained open-weight checkpoint
- Separate Max service configuration
Supervised fine-tuning · background →Preference learning · background →Stateful agent training · background →
No named optimizer, reward mixture or stage-by-stage training schedule is specified in this card. The method links are background, not claims of adoption; open weights and the Max service remain separate model identities.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗
- GPQA Diamond Benchmark | Artificial Analysis ↗
- 𝜏³-Banking Benchmark | Artificial Analysis ↗
- Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗
- Scale Labs — evaluation methodology and results ↗
Names used in source tables
Qwen3.8 2.4T A95B · Qwen3.8-2.4T-A95B (xHigh)