Hermes 4 405B vs Kimi K2 Instruct 0905 vs Qwen3 Max Preview
Too close to call on our weighted score (Kimi K2 Instruct 0905 38, Hermes 4 405B 35, Qwen3 Max Preview 33). The right pick depends on what you value most.
Nous ResearchHermes 4 405B
35/100- ECI—
- Price$1.00 / $3.00
- Context131K
Moonshot AIKimi K2 Instruct 0905
38/100- ECI—
- Price$0.60 / $2.50
- Context262K
Alibaba (Qwen)Qwen3 Max Preview
33/100- ECI—
- Price$0.975 / $4.14
- Context262K
Too close to call
It is close. Our weighted score puts them within 3 points (Kimi K2 Instruct 0905 38/100, Hermes 4 405B 35/100, Qwen3 Max Preview 33/100), so choose by what matters most for your work: Kimi K2 Instruct 0905 on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceKimi K2 Instruct 0905Kimi K2 Instruct 0905 $1.07 · Hermes 4 405B $1.50 · Qwen3 Max Preview $1.77 per 1M tokens (3:1 blend)
- Longest contextKimi K2 Instruct 0905 and Qwen3 Max PreviewKimi K2 Instruct 0905 262,144 · Qwen3 Max Preview 262,144 · Hermes 4 405B 131,072 tokens
- Widest inputsSame inputsHermes 4 405B: Text · Kimi K2 Instruct 0905: Text · Qwen3 Max Preview: Text
- Self-hostingHermes 4 405B and Kimi K2 Instruct 0905Publishes downloadable weights (Modified MIT)
| Measure | Weight | Hermes 4 405B | Kimi K2 Instruct 0905 | Qwen3 Max Preview |
|---|---|---|---|---|
| Price | 50% | 40 | 46 | 37 |
| Inputs & features | 30% | 35 | 25 | 25 |
| Context window | 20% | 25 | 37 | 37 |
| Overall | 100% | 35/100 | 38/100 | 33/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Hermes 4 405BNous Research | Kimi K2 Instruct 0905Moonshot AI | Qwen3 Max PreviewAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.00 | $0.60 (best) | $0.975 |
| Output | $3.00 | $2.50 (best) | $4.14 |
| Cached input | — | — | — |
| Blended (3:1) | $1.50 | $1.07 (best) | $1.77 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 5 providers | Median of 12 providers | Median of 2 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Max output | 117,964 tokens (best) | 98,304 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenModified MIT | Proprietary |
| API model ID | — | — | — |
| API providers | 5 | 13 (best) | 2 |
| Released | Aug 26, 2025 | Sep 5, 2025 | Sep 5, 2025 |
| Knowledge cutoff | Aug 31, 2024 | — | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Hermes 4 405B$16.00
- Kimi K2 Instruct 0905$11.00
- Qwen3 Max Preview$18.03
Which should you choose?
Which is better: Hermes 4 405B, Kimi K2 Instruct 0905 or Qwen3 Max Preview?
It is close. Our weighted score puts them within 3 points (Kimi K2 Instruct 0905 38/100, Hermes 4 405B 35/100, Qwen3 Max Preview 33/100), so choose by what matters most for your work: Kimi K2 Instruct 0905 on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Hermes 4 405B, Kimi K2 Instruct 0905 or Qwen3 Max Preview?
Kimi K2 Instruct 0905 is cheaper at $0.60 input / $2.50 output per million tokens (median across 12 API providers). Hermes 4 405B costs $1.00 input / $3.00 output per million tokens (median across 5 API providers); Qwen3 Max Preview costs $0.975 input / $4.14 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $1.07 per million tokens for Kimi K2 Instruct 0905 versus $1.50 for Hermes 4 405B (1.4× as much) and $1.77 for Qwen3 Max Preview (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Hermes 4 405B has not been scored yet, Kimi K2 Instruct 0905 has not been scored yet and Qwen3 Max Preview has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Hermes 4 405B, Kimi K2 Instruct 0905 and Qwen3 Max Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Kimi K2 Instruct 0905 and Qwen3 Max Preview have the largest context windows (262,144 and 262,144 tokens), against 131,072 for Hermes 4 405B. Maximum output per response: Hermes 4 405B up to 117,964, Kimi K2 Instruct 0905 up to 98,304, Qwen3 Max Preview up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Hermes 4 405B accepts text; Kimi K2 Instruct 0905 accepts text; Qwen3 Max Preview accepts text. They handle the same number of input types.
Are any of these open source?
Hermes 4 405B and Kimi K2 Instruct 0905 publishes its weights (Modified MIT) and can be self-hosted; Qwen3 Max Preview is proprietary.
Which is newer?
Kimi K2 Instruct 0905 is the newest, released Sep 5, 2025. Qwen3 Max Preview came out Sep 5, 2025; Hermes 4 405B came out Aug 26, 2025. Knowledge cutoff: Hermes 4 405B Aug 31, 2024, Qwen3 Max Preview Apr 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
