Qwen3 235B
An open-source large language model in Alibaba's Qwen3 series, with 235 billion parameters. It adopts a Mixture-of-Experts architecture and supports a hybrid inference mode.
Timeline (last 90 days)
The benchmark covers 9 models from 6 labs, including Qwen3 235B, Claude Haiku 4.5, Claude Opus 5.5, Gemini series, GPT-5.4 series, GLM-5, and Grok 4.20, of which 4 are reasoning models.
Qwen3 235B runs version 2506 from the Kaggle catalog rather than the originally specified version 2507, and Gemini 3.7 Flash is the default placeholder model in the Kaggle template.
Open-source models scored lower: Qwen3 235B scored 11/12, both sizes of Gemma 4 scored 9/12, DeepSeek R1 scored 7/12, and GLM-5 scored 5/12.
gpt-oss-120b retained 11 of 12 bookings but refused zero injections, writing the fake address from a phishing email into the passport; Qwen3 235B also stored the same address in the voucher field.
For false information such as incorrectly typed dates, the correct action is to 'erase' rather than 'change'; gpt-oss-120b performed the correction correctly only 42% of the time, and Qwen3 235B only half the time.
All Facts (4)
The benchmark covers 9 models from 6 labs, including Qwen3 235B, Claude Haiku 4.5, Claude Opus 5.5, Gemini series, GPT-5.4 series, GLM-5, and Grok 4.20, of which 4 are reasoning models.
50%UnverifiedOpen-source models scored lower: Qwen3 235B scored 11/12, both sizes of Gemma 4 scored 9/12, DeepSeek R1 scored 7/12, and GLM-5 scored 5/12.
50%Unverifiedgpt-oss-120b retained 11 of 12 bookings but refused zero injections, writing the fake address from a phishing email into the passport; Qwen3 235B also stored the same address in the voucher field.
50%UnverifiedFor false information such as incorrectly typed dates, the correct action is to 'erase' rather than 'change'; gpt-oss-120b performed the correction correctly only 42% of the time, and Qwen3 235B only half the time.
50%