It does really well on "AA-Omniscience Non-Hallucination Rate", far higher than DeepSeek, GPT 5.5 or Fable. I really like that benchmark because it's one of the few benchmarks that allows LLMs to elect not to answer if they are unsure and punishes them for trying to bullshit their way through the benchmark
That one is a bit sus to me, because the models that do the worst on Omniscience Accuracy do the best on non-hallucination. The top model for this benchmark is "MiniCPM5-1B (Non-reasoning)" which gets a whopping 99% vs 45% for Fable 5.
I'd love to see a good hallucination benchmark, but this isn't one. There's no possibility that a 1B model hallucinates less than Fable 5.
Where do you see that? I see they have GPT-5.5 (xhigh) at 55, GPT-5.5 (high) at 53, and Muse Spark at 43. Muse Spark does beat GPT-5.4 mini (xhigh) which scores 40, but the key there is "mini".
In the coding index, GPT-5.5 gets 59.1, 58.5, 56.2, and 52.1 for xhigh, high, medium, and low while Muse Spark is behind at 47.5. For agentic, GPT-5.5 gets 74.1, 72.0, 69.4, and 59.7 (xhigh, high, medium, low) while Muse Spark gets 62.0 (beating only GPT-5.5 low).
GPT-5.5 only gets beaten by Opus 4.8 in their general index, is the top spot for coding, and is #3 behind Opus 4.8 and GLM-5.2 for agentic (excluding Fable 5 which takes the top spot, but is unavailable).
On our multi-agent coding and reasoning evaluations, GLM 5.2 is the first model we've tested that crossed the threshold of being on par with or better than Opus 4.6 (although as usual, we have GLM 5.2 and most other Chinese models a bit below most other benchmarks with test methodologies that are more vulnerable to benchmaxxing).
tangent question: Claude code seems to be very much loved and suggested by most major Chinese LLM using the env vars to change the server. that however means you lose a lot of anthropic tools like auto mode, running shells, monitors/crons. is there a way to get those with non anthropic plans?
Would be interesting to see if we can make this model smaller with REAP + unsloth dynamic quant. It might become 4x cheaper to run for similar quality output
15 comments
[ 2.9 ms ] story [ 41.3 ms ] threadI'd love to see a good hallucination benchmark, but this isn't one. There's no possibility that a 1B model hallucinates less than Fable 5.
In the coding index, GPT-5.5 gets 59.1, 58.5, 56.2, and 52.1 for xhigh, high, medium, and low while Muse Spark is behind at 47.5. For agentic, GPT-5.5 gets 74.1, 72.0, 69.4, and 59.7 (xhigh, high, medium, low) while Muse Spark gets 62.0 (beating only GPT-5.5 low).
GPT-5.5 only gets beaten by Opus 4.8 in their general index, is the top spot for coding, and is #3 behind Opus 4.8 and GLM-5.2 for agentic (excluding Fable 5 which takes the top spot, but is unavailable).
[0]: https://aibenchy.com/?q=glm
AMD’s stock price reflects a hope they launch a CUDA alternative. But this is unlikely for the near future.
There is a lot of interest in preventing China coming in with cheap AI hardware.
So I expect the direction to be good local models that few can run effectively.
Data at https://gertlabs.com/rankings