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 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
GSM8K Chat leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | NV | 81.9% | 100.0% | 1 | C |
GSM8K Chat highlights
The top published results on this benchmark's own scale.
What is GSM8K Chat?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- GSM8K Chat
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gsm8k-chat|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.