Kimi K2 8B on MATH-500: score, rank and what it means
Kimi K2 8B scores 68.7 on MATH-500, placing it #392 of 600 models in the index. The benchmark average is 72.5 and the leader is GPT-5.2 Max at 96.7.
Score distribution
The chart shows the top 10 models on MATH-500, with Kimi K2 8B highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 2 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 3 | GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| 4 | o4 Reasoning | OpenAI | 1000000 | $19.69 | 87.5 |
| 5 | Grok 4 Max | xAI | 2000000 | $19.70 | 86.6 |
| 6 | Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| 7 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 8 | Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| 9 | Gemini 3 Pro Reasoning | Google DeepMind | 200000 | $19.69 | 87.5 |
| 10 | Claude Opus 4.5 Turbo | Anthropic | 2000000 | $19.57 | 85.7 |
What this score means
On MATH-500, Kimi K2 8B sits at #392 of 600. The leader, GPT-5.2 Max, scores 96.7, so the gap to the top is 28.0 points. The median model in this index scores 76.0, which puts Kimi K2 8B below the midpoint.
Moonshot AI models average 74.0 on this benchmark. Kimi K2 8B is 5.3 points below that provider line, so it is a weaker result than the average Moonshot AI model.
Among small open-weight models, the average is 53.7. Kimi K2 8B is 15.0 points above that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 68.7 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.
Price context
At $1.86 per million input tokens, Kimi K2 8B is below the median input price of $4.00 across the 600 models scored on MATH-500. The models immediately around it in the ranking are shown below so you can compare score and price together.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Phi-3.5 Chat | Microsoft | 16384 | $2.64 | 69.0 |
| Sonar Pro Nano | Perplexity | 32768 | $5.50 | 66.1 |
| Command A Nano | Cohere | 8192 | $5.90 | 66.3 |
| Embed 4 Turbo | Cohere | 4096 | $5.13 | 64.0 |
| Kimi K2 8B | Moonshot AI | 8192 | $1.86 | 64.7 |
| Molmo Instruct | Allen Institute for AI | 32768 | $2.53 | 68.3 |
| Firesearch | Fireworks AI | 32768 | $7.03 | 68.5 |
Other benchmarks for Kimi K2 8B
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 67.3 | 427 | 29th | |
| GPQA Diamond | 59.3 | 411 | 32th | |
| SWE-bench Verified | 50.9 | 414 | 31th | |
| HumanEval | 69.9 | 395 | 34th | |
| AIME 2025 | 55.4 | 414 | 31th | |
| LiveCodeBench | 55.0 | 406 | 32th | |
| IFEval | 75.4 | 394 | 34th | |
| TruthfulQA | 69.4 | 404 | 33th | |
| HellaSwag | 78.6 | 398 | 34th | |
| MMMU | 62.2 | 406 | 32th | |
| Arena Elo | 1311.4 | 406 | 32th |
FAQ
What score does Kimi K2 8B get on MATH-500?
Kimi K2 8B scores 68.7 on MATH-500 in this index. The benchmark average is 72.5 and the top score is 96.7.
How does Kimi K2 8B rank on MATH-500?
It ranks #392 of 600 models, in the 35th percentile. The leader is GPT-5.2 Max at 96.7.
Is Kimi K2 8B good at MATH-500?
It is below the median for this benchmark, so test it carefully before relying on it for this capability. The result should be read alongside its price and context window.
How is the MATH-500 score calculated?
MATH-500 is a mathematics benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.
What does Kimi K2 8B cost?
Kimi K2 8B costs $1.86 per million input tokens and $10.03 per million output tokens.