math benchmark
GSM8K Chat
Grade School Math 8K adapted for chat format evaluation, featuring 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
GSM8K Chat Ranking
Higher score ranks better on this benchmark.
| 1 | NV | 81.9% | 100.0% | 1 | C |
GSM8K Chat Highlights
The leading models and scores on this benchmark.
What is GSM8K Chat?
What GSM8K Chat measures and how its scores work.
Grade School Math 8K adapted for chat format evaluation, featuring 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GSM8K Chat
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gsm8k-chat|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GSM8K Chat.
Which model scores highest on GSM8K Chat?
Llama 3.1 Nemotron 70B Instruct is currently ranked first with 81.9%.
What does GSM8K Chat measure?
Grade School Math 8K adapted for chat format evaluation, featuring 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.