← Models

Model profile

Qwen3-Coder 480B A35B Instruct

Alibabadeveloper
2025-07-22release date
#195 / 333Safety rank
#379 / 645Freedom rank

Evidence summary

Safety. Qwen3-Coder 480B A35B Instruct has an estimated Safety rank of #195; its 90% source-sensitivity interval is #23–#308. Its behavior-only rank is #188; company governance moves the combined estimate to #195. Published Safety evidence spans 4 eval lineages and 2 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #66 of 345); its weakest is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #88 of 111).

Freedom. Qwen3-Coder 480B A35B Instruct has an estimated Freedom rank of #379; its 90% source-sensitivity interval is #209–#558. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #47 of 104); its weakest is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #47 of 104).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
AA-Omnisciencehallucination_rate#66 / 3450.4493Source ↗official
Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating#88 / 1111417.0Source ↗official
BullshitBench v2clear_pushback_rate#74 / 1170.2Source ↗official
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#58 / 10440.78Source ↗official

Freedom evals

Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#47 / 10440.78Source ↗official