Model comparison
GPT-6 Astra vs Hermes 4 405B
GPT-6 Astra has enough public results to be ranked (#1); Hermes 4 405B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. GPT-6 Astra scores higher in 2 categories and Hermes 4 405B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 25.3.
- Hermes 4 405B is cheaper at $1 / $3 per million input/output tokens, against $10 / $50 for GPT-6 Astra.
- GPT-6 Astra accepts more context: 1.05M tokens versus 131K.
- Hermes 4 405B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Astra | Hermes 4 405B | |
|---|---|---|
| Provider | OpenAI | Nous Research |
| Noometry Index | 70.3 | 37.1 |
| Released | 2026-09-03 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 118K |
| Input $ / M tokens | $10 | $1 |
| Output $ / M tokens | $50 | $3 |
| Results tracked | 51 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-6 Astra: 70.5 (#3), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| LMArena WebDev | 1792 | — |
| FrontierSWE | 65.5% | — |
| SciCode | 56.5% | — |
| WeirdML | 93.6% | — |
| LMArena Coding | 1488 | — |
| MirrorCode | 46.7% | — |
| ALE-Bench | 2,951 | — |
Agentic & Tool Use Not comparable
GPT-6 Astra: 52.3 (#3), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Remote Labor Index | 20.8% | — |
| BALROG | 68.3% | — |
| Vending-Bench 2 | 15,515 | — |
Reasoning GPT-6 Astra leads
GPT-6 Astra: 85.1 (#1), Hermes 4 405B: 25.3
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| ARC-AGI-2 | 95% | — |
| Kagi LLM Benchmark | — | 55.8% |
| NYT Connections (extended) | 98.1% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| Chess Puzzles | 72% | — |
| EBR-Bench | 76.2% | — |
| LMArena Hard Prompts | 1464 | — |
| Mystery Game Puzzles | 84% | — |
| DTBench | 97.3% | — |
| LMCA | 64.4% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 166.6 | — |
Math Not comparable
GPT-6 Astra: 93.4 (#1), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 97.6% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 99% | — |
| LMArena Math | 1463 | — |
| FrontierMath Erdős | 2.9% | — |
Knowledge Not comparable
GPT-6 Astra: 75.3 (#1), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| GPQA Diamond | 95.8% | — |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| Vectara Hallucination Rate | 8.7% | — |
| LMArena Expert | 1486 | — |
Multimodal Not comparable
GPT-6 Astra: 55.1 (#3), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| LMArena Vision | 1280 | — |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |
Multilingual Not comparable
GPT-6 Astra: 54.0 (#53), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1467 | — |
| LMArena Russian | 1434 | — |
| LMArena Spanish | 1412 | — |
Instruction Following Not comparable
GPT-6 Astra: 76.6 (#37), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| LMArena Instruction Following | 1454 | — |
Long Context Not comparable
GPT-6 Astra: 44.7 (#57), Hermes 4 405B: —
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| LMArena Longer Query | 1460 | — |
Writing & Preference GPT-6 Astra leads
GPT-6 Astra: 75.7 (#7), Hermes 4 405B: 53.0
| Benchmark | GPT-6 Astra | Hermes 4 405B |
|---|---|---|
| EQ-Bench Creative Writing | 2173 | 1421 |
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1423 | — |
| LMArena Multi-Turn | 1457 | — |
Frequently asked questions
Is GPT-6 Astra better than Hermes 4 405B?
GPT-6 Astra has enough public results to be ranked (#1); Hermes 4 405B does not yet, so treat this comparison as directional.
Which is cheaper, GPT-6 Astra or Hermes 4 405B?
Hermes 4 405B is cheaper. It lists at $1 per million input tokens and $3 per million output tokens; GPT-6 Astra lists at $10 and $50.
Which has the bigger context window?
GPT-6 Astra does, with 1.05M tokens against 131K.
How many benchmarks do GPT-6 Astra and Hermes 4 405B share?
1 benchmark has published results for both models. GPT-6 Astra has 51 scored results on Noometry and Hermes 4 405B has 2.