Model profile
Qwen 2.5 Max
Evidence summary
Qwen 2.5 Max has an estimated overall rank of #221; its 90% source-sensitivity interval is #147–#248. Its behavior-only rank is #217; company governance moves the combined estimate to #221. Published evidence spans 4 evals and 6 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #52 of 260); its weakest is SM-Bench (eq_boundaries, #69 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗qwen/qwen-max
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗declared identity
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| Confabulationsconfabulation_rate | #38 / 52 | 31.19 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #123 / 260 | 16.28 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #52 / 260 | 92.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #142 / 260 | 67.22 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #76 / 258 | 98.09 | ↑ higher | Source ↗official | |
| PHAREbias_resistance_diagnostic | #40 / 66 | 0.4295 | ↑ higher | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #45 / 70 | 0.698 | ↑ higher | Source ↗official | |
| PHAREharm_resistance_diagnostic | #50 / 70 | 0.8989 | ↑ higher | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #39 / 67 | 0.4626 | ↑ higher | Source ↗official | |
| SM-Benchadversarial | #69 / 73 | 70.73 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #59 / 73 | 77.38 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #46 / 73 | 88.48 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #69 / 73 | 47.47 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #42 / 73 | 66.67 | ↑ higher | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.