DeepSeek-Coder Base on MATH-500: score, rank and what it means
DeepSeek-Coder Base scores 74.2 on MATH-500, placing it #341 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 DeepSeek-Coder Base 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, DeepSeek-Coder Base sits at #341 of 600. The leader, GPT-5.2 Max, scores 96.7, so the gap to the top is 22.5 points. The median model in this index scores 76.0, which puts DeepSeek-Coder Base below the midpoint.
DeepSeek models average 74.2 on this benchmark. DeepSeek-Coder Base is 0.0 points below that provider line, so it is a weaker result than the average DeepSeek model.
Among coding models, the average is 71.0. DeepSeek-Coder Base is 3.2 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 74.2 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 $3.53 per million input tokens, DeepSeek-Coder Base 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 |
|---|---|---|---|---|
| Firefunction Pro | Fireworks AI | 16384 | $9.05 | 72.9 |
| Phi-3.5 Instruct | Microsoft | 16384 | $2.67 | 70.1 |
| o3 Nano | OpenAI | 32768 | $7.78 | 70.6 |
| Arctic Instruct | Snowflake | 65536 | $2.83 | 70.6 |
| DeepSeek-Coder Base | DeepSeek | 32768 | $3.53 | 74.1 |
| Llama 3.1 Cerebras Base | Cerebras | 65536 | $3.36 | 72.7 |
| Auto | OpenRouter | 32768 | $7.53 | 70.2 |
Other benchmarks for DeepSeek-Coder Base
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 78.9 | 211 | 65th | |
| GPQA Diamond | 70.8 | 240 | 60th | |
| SWE-bench Verified | 59.3 | 337 | 44th | |
| HumanEval | 78.4 | 283 | 53th | |
| AIME 2025 | 71.7 | 223 | 63th | |
| LiveCodeBench | 67.3 | 242 | 60th | |
| IFEval | 81.6 | 282 | 53th | |
| TruthfulQA | 79.0 | 215 | 64th | |
| HellaSwag | 84.8 | 255 | 58th | |
| MMMU | 69.0 | 325 | 46th | |
| Arena Elo | 1388.5 | 255 | 58th |
FAQ
What score does DeepSeek-Coder Base get on MATH-500?
DeepSeek-Coder Base scores 74.2 on MATH-500 in this index. The benchmark average is 72.5 and the top score is 96.7.
How does DeepSeek-Coder Base rank on MATH-500?
It ranks #341 of 600 models, in the 43rd percentile. The leader is GPT-5.2 Max at 96.7.
Is DeepSeek-Coder Base 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 DeepSeek-Coder Base cost?
DeepSeek-Coder Base costs $3.53 per million input tokens and $12.53 per million output tokens.