Compare · ModelsLive · 2 picked · head to head
MPT-30B vs DeepSeek Coder 33B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
MPT-30B wins on 3/4 benchmarks
MPT-30B wins 3 of 4 shared benchmarks. Leads in knowledge.
Category leads
knowledge·MPT-30Bmath·DeepSeek Coder 33B
Hype vs Reality
Attention vs performance
MPT-30B
#182 by perf·no signal
DeepSeek Coder 33B
#203 by perf·no signal
Vendor risk
Mixed exposure
One or more vendors flagged
U
Unknown
private · undisclosed
DeepSeek
$3.4B·Tier 1
Head to head
4 benchmarks · 2 models
MPT-30BDeepSeek Coder 33B
ARC AI2
MPT-30B leads by +11.2
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
MPT-30B
34.1
DeepSeek Coder 33B
22.9
GSM8K
DeepSeek Coder 33B leads by +1.0
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
MPT-30B
34.4
DeepSeek Coder 33B
35.4
MMLU
MPT-30B leads by +11.3
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
MPT-30B
30.5
DeepSeek Coder 33B
19.2
Winogrande
MPT-30B leads by +18.0
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
MPT-30B
42.0
DeepSeek Coder 33B
24.0
Full benchmark table
| Benchmark | MPT-30B | DeepSeek Coder 33B |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 34.1 | 22.9 |
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 34.4 | 35.4 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 30.5 | 19.2 |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | 42.0 | 24.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
U MPT-30B | — | — | — | — |
| — | — | — | — |