Model Comparison
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
vs. o3-mini (high)
Comparing 2 AI models · 11 benchmarks · Nous Research, OpenAI
Recommended Pick
Op o3-mini (high) 10 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
$0.00/1M input price
Best Reasoning
o3-mini (high)
59.9 reasoning score
Blends available reasoning benchmarks
Best for Coding
o3-mini (high)
17.3 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) is ∞x cheaper on input tokens than o3-mini (high).
Reasoning gap
o3-mini (high) leads DeepHermes 3 - Mistral 24B Preview (Non-reasoning) by 36.4 points on reasoning.
Top-pick rationale
o3-mini (high) wins 10 measurable categories, including Throughput, Reasoning, Intelligence, GPQA.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
Nous Research
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
o3-mini (high)
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | No DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Top Pick Op o3-mini (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $1.10/1M |
| Output Cost | $0.00/1M | $4.40/1M |
| Blended (3:1) | — | $1.93/1M |
| Specifications | ||
| Organization | Nous Research | OpenAI |
| Release Date | Mar 13, 2025 | Jan 31, 2025 |
| Performance & Speed | ||
| Throughput | — | 218.8 tok/s |
| TTFT | — | 19868ms |
| Latency | — | 19868ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 23.4 | 59.9 |
| Intelligence | 10.9 | 25.2 |
| Coding | — | 17.3 |
| Standard Benchmarks | ||
| GPQA | 38.2% | 77.3% |
| MMLU Pro | 58.0% | 80.2% |
| HLE | 3.9% | 12.3% |
| LiveCodeBench | 19.5% | 73.4% |
| MATH 500 | 59.5% | 98.5% |
| AIME (Original) | 4.7% | 86.0% |
| SciCode | 22.8% | 39.8% |
| LCR | — | 39.3% |
| IFBench | — | 67.1% |
| TAU-bench v2 | — | 31.3% |
| TerminalBench Hard | — | 6.1% |
Key Takeaways
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
o3-mini (high) has the strongest reasoning profile with a 59.9 reasoning score, combining the available reasoning-heavy benchmarks.
o3-mini (high) reaches a 17.3 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
o3-mini (high)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
