BenchmarkLLMsv1.0

Minerva Math

by Google Research · open-source · Last verified 2026-03-01

Quantitative reasoning benchmark spanning STEM subjects including math, physics, chemistry, and engineering. Evaluates models on problems requiring mathematical computation, symbolic manipulation, and scientific reasoning with numerical or symbolic answers.

https://github.com/google-research/minerva ↗

C+

C+—Average

Adoption: BQuality: AFreshness: B+Citations: BEngagement: F

Specifications

License: Apache-2.0
Pricing: open-source
Capabilities: model-evaluation, quantitative-reasoning-testing, stem-assessment
Integrations: lm-eval-harness
Use Cases: stem-evaluation, quantitative-reasoning-testing, scientific-computing-assessment
API Available: No
Evaluated Models: claude-4, gpt-5, gemini-2.5-pro, deepseek-v3
Metrics: accuracy, stem-accuracy
Methodology: STEM problems requiring mathematical computation and scientific reasoning. Models generate step-by-step solutions with final answers checked for correctness.
Last Run: 2026-01-25
Tags: benchmark, evaluation, mathematics, stem, quantitative
Added: 2026-03-17
Completeness: 100%

Index Score

58.9

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service