Chat with the newest AI models and work with them on your hardest problems
October 6, 2026 ·
Version 2 of our paper
Benchmarks in Leipzig
is now on arXiv.
We believe that the current way of submitting benchmark problems has reached its limits,
and we are looking into new ways of benchmarking.
In the meantime, we are closing the submission system.
September 28, 2026 ·
Now available:
GPT-6 Sol,
GPT-6 Astra and
Astra Pro from OpenAI,
Claude Opus 5.5 and
Claude Fable 5.1 from Anthropic.
September 28, 2026 ·
All 100 problems of the
Leipzig Benchmark
were re-run against the newest models, now including
GPT-6 Sol and
Claude Opus 5.5.
Four problems were solved by none of the leading models.
September 24, 2026 ·
You can now attach files to a chat.
These are read by the models and stay with the conversation. You can in
addition change the Thinking Effort
for each model individually.
Every user gets free monthly credit. Prepaid credit is available individually or as a shared pool for research groups and teams.
See My Chat or contact us for shared pools at contact@sciencebench.ai.
Newest Available Frontier Models:
GPT-6 Sol
$$$$
Claude Opus 5.5
$$$$
GPT-6 Astra
$$$$
Gemini 3.1 Pro
$$$$
Premium Models (only available for grant users):
GPT-6 Astra Pro
$$$$
Claude Fable 5.1
$$$$
337
researchers signed up
325
benchmark problems by 102 users
5147
chat turns by 171 users
See how the newest models perform on research-level mathematics.
Public BenchmarksBrowse research-level problems contributed by the community.
Sample Problems