Gemini 4 Argon vs Hermes 3 70B Instruct
Gemini 4 Argon leads Hermes 3 70B Instruct on the Artificial Analysis Intelligence Index, 52.6 to 6.7, and Hermes 3 70B Instruct costs 14.3x less per output token ($0.70 vs $10.00 per million). Updated October 23, 2026; 2 benchmarks have a result for both.
vs boards won of 2 shared
Gemini 4 Argon or Hermes 3 70B Instruct: which to pick
Only Gemini 4 Argon has a coding score, 80.9 on the Vibe Coding Index; Hermes 3 70B Instruct has none, so the two cannot be ranked on coding.
Pick Hermes 3 70B Instruct for output tokens 14.3x cheaper ($0.70 vs $10.00 per million).
Model AGemini 4 ArgonGoogle80.9/1005 independent benchmarksNo cost per solved taskModel BHermes 3 70B InstructNous ResearchNot benchmarkedNo coding benchmarkNo cost per solved task
- Shared results
- 2
- Gemini 4 Argon only
- 100
- Hermes 3 70B Instruct only
- 3
- Like-for-like categories
- 2 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Gemini 4 Argon has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemini 4 Argon
Gemini 4 Argon leads, 52.6 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 4 Argon has a Design Arena: websites result, 1316.
Directional only
General
Vals Index
No call
Only Gemini 4 Argon has a Vals Index result, 69.2%.
Directional only
Long documents
Listed context window
Gemini 4 Argon
Gemini 4 Argon takes 1.05M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hermes 3 70B Instruct
Gemini 4 Argon $0.0070, Hermes 3 70B Instruct $0.0010 per turn.
List prices
At a glance
- Coding index
- Gemini 4 Argon 80.9 from 5 benchmarks, Hermes 3 70B Instruct not benchmarked.
- Widest category
- Reasoning, 53.1 points apart on average over 1 shared benchmark.
- Widest single gap
- Humanity's Last Exam (Artificial Analysis run): Gemini 4 Argon 57.1% against Hermes 3 70B Instruct 4.0%, 53.1 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Argon $10.00 against Hermes 3 70B Instruct $0.70 per million output tokens, 14.3x apart.
- Context window
- Gemini 4 Argon takes 1.05M tokens, Hermes 3 70B Instruct 131K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 4 Argon | Bars | Hermes 3 70B Instruct | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| All shared boards | 2 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index23 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| LiveBench coding | 89.7% | Not measured | Only Gemini 4 Argon measured |
| LMArena WebDev | 1673 | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench 4 (Vals AI) | 57.6% | Not measured | Only Gemini 4 Argon measured |
| Vibe Code Bench (Vals AI) | 91.9% | Not measured | Only Gemini 4 Argon measured |
| Code migration (Vals AI) | 68.2% | Not measured | Only Gemini 4 Argon measured |
| ProgramBench (Vals AI) | 2.5% | Not measured | Only Gemini 4 Argon measured |
| IOI (Vals AI) | 100.0% | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench 2.1 (Vals AI) | 57.7% | Not measured | Only Gemini 4 Argon measured |
| SWE-bench Multimodal (Vals AI) | 56.0% | Not measured | Only Gemini 4 Argon measured |
| Vibe Code Bench 1-100 (Vals AI) | 21.2% | Not measured | Only Gemini 4 Argon measured |
| CyberBench (Vals AI) | 77.9% | Not measured | Only Gemini 4 Argon measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 18.8% | Only Hermes 3 70B Instruct measured |
| SciCode | 61.8% | Not measured | Only Gemini 4 Argon measured |
| FrontierCode | 47.5% | Not measured | Only Gemini 4 Argon measured |
| FrontierSWE | 55.0% | Not measured | Only Gemini 4 Argon measured |
| MirrorCode | 58.9% | Not measured | Only Gemini 4 Argon measured |
| ALE-Bench | 2100.1 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: coding | 1539 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: software and IT | 1544 | Not measured | Only Gemini 4 Argon measured |
| LMArena WebDev: React | 1688 | Not measured | Only Gemini 4 Argon measured |
| LMArena WebDev: HTML | 1640 | Not measured | Only Gemini 4 Argon measured |
| SciCode | 12.3% | Not measured | Only Gemini 4 Argon measured |
| SWE-Bench Pro V2 | 99.2% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 52.6 | 6.7 | Gemini 4 Argon |
| Epoch Capabilities Index | 166.4 | Not measured | Only Gemini 4 Argon measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| Design Arena: spreadsheets | 1172 | Not measured | Only Gemini 4 Argon measured |
| LiveBench research | 83.1% | Not measured | Only Gemini 4 Argon measured |
| LiveBench browser | 92.0% | Not measured | Only Gemini 4 Argon measured |
| LiveBench long agentic | 69.9% | Not measured | Only Gemini 4 Argon measured |
| SREBench (Vals AI) | 44.3% | Not measured | Only Gemini 4 Argon measured |
| Finance Agent (Vals AI) | 65.4% | Not measured | Only Gemini 4 Argon measured |
| Tax Agent Bench (Vals AI) | 44.6% | Not measured | Only Gemini 4 Argon measured |
| Legal Research Bench (Vals AI) | 54.8% | Not measured | Only Gemini 4 Argon measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 27.1% | Not measured | Only Gemini 4 Argon measured |
| Excel Modeling Benchmark (Vals AI) | 75.2% | Not measured | Only Gemini 4 Argon measured |
| BioMysteryBench (Vals AI) | 76.3% | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench-Science (Vals AI) | 44.3% | Not measured | Only Gemini 4 Argon measured |
| Vals Science Index | 55.4% | Not measured | Only Gemini 4 Argon measured |
| Time Horizon Index (Vals AI) | 52.5% | Not measured | Only Gemini 4 Argon measured |
| CUA-bench (Vals AI) | 4.8% | Not measured | Only Gemini 4 Argon measured |
| Robo-bench (Vals AI) | 0.8% | Not measured | Only Gemini 4 Argon measured |
| APEX-Agents | 82.4% | Not measured | Only Gemini 4 Argon measured |
| Vending-Bench 2 | $13,718 | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| LiveBench reasoning | 95.1% | Not measured | Only Gemini 4 Argon measured |
| MysteryMechanism (Vals AI) | 45.5% | Not measured | Only Gemini 4 Argon measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 40.1% | Only Hermes 3 70B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | 57.1% | 4.0% | Gemini 4 Argon |
| GPQA Diamond (Epoch AI run) | 96.4% | Not measured | Only Gemini 4 Argon measured |
| ARC-AGI | 98.5% | Not measured | Only Gemini 4 Argon measured |
| ARC-AGI-2 | 91.3% | Not measured | Only Gemini 4 Argon measured |
| Chess puzzles | 59.0% | Not measured | Only Gemini 4 Argon measured |
| Mystery game puzzles | 64.0% | Not measured | Only Gemini 4 Argon measured |
| EBR-bench | 64.8% | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: hard prompts | 1538 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: expert | 1545 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: hard prompts in English | 1534 | Not measured | Only Gemini 4 Argon measured |
| Humanity's Last Exam (Scale run) | 53.2% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 9 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Gemini 4 Argon measured |
| FrontierMath, tiers 1 to 3 | 86.0% | Not measured | Only Gemini 4 Argon measured |
| FrontierMath, tier 4 | 78.0% | Not measured | Only Gemini 4 Argon measured |
| ProofBench | 99.0% | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: math | 1538 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: mathematical work | 1549 | Not measured | Only Gemini 4 Argon measured |
| MathArena | 69.3% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 88.3% | Not measured | Only Gemini 4 Argon measured |
| MedCode (Vals AI) | 58.8% | Not measured | Only Gemini 4 Argon measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 57.1% | Only Hermes 3 70B Instruct measured |
| SimpleQA Verified | 76.0% | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: science | 1542 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: medicine and healthcare | 1537 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: legal and government | 1527 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: business and finance | 1512 | Not measured | Only Gemini 4 Argon measured |
| PRBench Finance | 49.9% | Not measured | Only Gemini 4 Argon measured |
| PRBench Legal | 49.4% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1316 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: UI components | 1333 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: game dev | 1376 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: data viz | 1331 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: 3D | 1386 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: all code categories | 1329 | Not measured | Only Gemini 4 Argon measured |
| LiveBench design | 73.7% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index24 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| Vals Index | 69.2% | Not measured | Only Gemini 4 Argon measured |
| LiveBench data analysis | 85.2% | Not measured | Only Gemini 4 Argon measured |
| Public Benefits Bench (Vals AI) | 69.8% | Not measured | Only Gemini 4 Argon measured |
| SAGE (Vals AI) | 53.6% | Not measured | Only Gemini 4 Argon measured |
| MedScribe (Vals AI) | 87.4% | Not measured | Only Gemini 4 Argon measured |
| Long context reasoning (AA-LCR) | 79.7% | Not measured | Only Gemini 4 Argon measured |
| DTBench | 97.6% | Not measured | Only Gemini 4 Argon measured |
| LMCA | 63.7% | Not measured | Only Gemini 4 Argon measured |
| Furniture assembly | 72.5% | Not measured | Only Gemini 4 Argon measured |
| LMArena Text | 1526 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: instruction following | 1528 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: creative writing | 1523 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: English | 1526 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: non-English | 1519 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Chinese | 1600 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: French | 1543 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Spanish | 1508 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Russian | 1537 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Polish | 1530 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: multi-turn | 1547 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: longer queries | 1538 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: writing and language | 1524 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: entertainment and media | 1517 | Not measured | Only Gemini 4 Argon measured |
| MultiChallenge | 78.7% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Argon | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 4 Argon$0.0070Fits in one request
Hermes 3 70B Instruct$0.0010Fits in one request
Hermes 3 70B Instruct costs less
Repository review
50K input + 3K output tokens
Gemini 4 Argon$0.130Fits in one request
Hermes 3 70B Instruct$0.037Fits in one request
Hermes 3 70B Instruct costs less
Agent loop
200K input + 10K output tokens
Gemini 4 Argon$0.500Fits in one request
Hermes 3 70B Instruct$0.147Exceeds the context window
Hermes 3 70B Instruct costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 4 Argon | Nous Hermes 3 70B Instruct |
|---|---|---|
| Maker | Nous Research | |
| Weights | No public weights listed | Open weights |
| Released | October 13, 2026 | August 18, 2024 |
| Context window | 1.05M | 131K |
| Input $/Mtok | $2.00 | $0.70 |
| Output $/Mtok | $10.00 | $0.70 |
| Coding index | 80.9 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Argon better than Hermes 3 70B Instruct for coding?
Only Gemini 4 Argon has a coding score, 80.9 on the Vibe Coding Index; Hermes 3 70B Instruct has none, so the two cannot be ranked on coding. Pick Hermes 3 70B Instruct for output tokens 14.3x cheaper ($0.70 vs $10.00 per million).
Which is cheaper, Gemini 4 Argon or Hermes 3 70B Instruct?
Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; Hermes 3 70B Instruct costs $0.70 and $0.70. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemini 4 Argon or Hermes 3 70B Instruct?
Gemini 4 Argon, with 1.05M tokens against 131K.
How many benchmarks is the Gemini 4 Argon vs Hermes 3 70B Instruct comparison based on?
2 benchmarks have a result for both models as of October 23, 2026. Gemini 4 Argon's coding index rests on 5 independent benchmarks and Hermes 3 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.