Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemma 4 31B (Non-reasoning) | Hermes 4 - Llama-3.1 70B (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.14 | $0.13 |
| Output ($/M tokens) | $0.4 | $0.4 |
Data from Artificial Analysis API — 12 benchmarks
Hermes 4 - Llama-3.1 70B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.20/M tokens vs $0.20/M for Gemma 4 31B (Non-reasoning).
Gemma 4 31B (Non-reasoning) wins 6 out of 12 benchmarks compared to 4 for Hermes 4 - Llama-3.1 70B (Non-reasoning). See the detailed benchmark chart above for per-category results.
Hermes 4 - Llama-3.1 70B (Non-reasoning) generates tokens faster at 95 tok/s vs 55 tok/s. However, Hermes 4 - Llama-3.1 70B (Non-reasoning) has lower time-to-first-token (0.58s vs 0.77s).
Choose based on your priorities: Hermes 4 - Llama-3.1 70B (Non-reasoning) for lower cost, Gemma 4 31B (Non-reasoning) for stronger benchmark performance, and Hermes 4 - Llama-3.1 70B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.