Phi 4 vs Hermes 3 70B Instruct
Hermes 3 70B Instruct leads Phi 4 on the Artificial Analysis Intelligence Index, 6.7 to 5.9, and Phi 4 costs 5.0x less per output token ($0.14 vs $0.70 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
Phi 4 or Hermes 3 70B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Phi 4 for output tokens 5.0x cheaper ($0.14 vs $0.70 per million) and work measured by AA Intelligence Index or Humanity's Last Exam (Artificial Analysis run), where it leads.
- Shared results
- 5
- Phi 4 only
- 41
- Hermes 3 70B Instruct only
- 0
- Like-for-like categories
- 4 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Hermes 3 70B Instruct
Hermes 3 70B Instruct leads, 6.7 against 5.9.
Same board, both measured
Long documents
Listed context window
Hermes 3 70B Instruct
Hermes 3 70B Instruct takes 131K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Hermes 3 70B Instruct $0.0010 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, Hermes 3 70B Instruct not benchmarked.
- Widest category
- Knowledge, 14.3 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): Phi 4 57.5% against Hermes 3 70B Instruct 40.1%, 17.4 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Hermes 3 70B Instruct $0.70 per million output tokens, 5.0x apart.
- Context window
- Phi 4 takes 16K 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 | Phi 4 | Bars | Hermes 3 70B Instruct | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 1 | 1 | ||
| Knowledge | 1 | 0 | ||
| All shared boards | 3 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 23.1% | 18.8% | Phi 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | Not measured | Only Phi 4 measured |
| LMArena Text: coding | 1231 | Not measured | Only Phi 4 measured |
| LMArena Text: software and IT | 1228 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 6.7 | Hermes 3 70B Instruct |
| Epoch Capabilities Index | 130.5 | Not measured | Only Phi 4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 0.0% | Not measured | Only Phi 4 measured |
| BALROG | 11.6% | Not measured | Only Phi 4 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 28.8% | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.5% | 40.1% | Phi 4 |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 4.0% | Hermes 3 70B Instruct |
| GPQA Diamond (Epoch AI run) | 56.1% | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts | 1220 | Not measured | Only Phi 4 measured |
| LMArena Text: expert | 1203 | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts in English | 1230 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 18.0 | Not measured | Only Phi 4 measured |
| AIME 2025 (Artificial Analysis run) | 18.0% | Not measured | Only Phi 4 measured |
| OTIS Mock AIME | 13.8% | Not measured | Only Phi 4 measured |
| MATH level 5 | 64.9% | Not measured | Only Phi 4 measured |
| LMArena Text: math | 1246 | Not measured | Only Phi 4 measured |
| LMArena Text: mathematical work | 1254 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 71.4% | 57.1% | Phi 4 |
| MMLU | 84.8% | Not measured | Only Phi 4 measured |
| LMArena Text: science | 1206 | Not measured | Only Phi 4 measured |
| LMArena Text: medicine and healthcare | 1202 | Not measured | Only Phi 4 measured |
| LMArena Text: legal and government | 1241 | Not measured | Only Phi 4 measured |
| LMArena Text: business and finance | 1199 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
| Benchmark | Phi 4 | Hermes 3 70B Instruct | Leader |
|---|---|---|---|
| IFBench | 23.5% | Not measured | Only Phi 4 measured |
| Long context reasoning (AA-LCR) | 0.0% | Not measured | Only Phi 4 measured |
| Creative writing (Lech Mazur) | 62.6% | Not measured | Only Phi 4 measured |
| LMArena Text | 1217 | Not measured | Only Phi 4 measured |
| LMArena Text: instruction following | 1201 | Not measured | Only Phi 4 measured |
| LMArena Text: creative writing | 1181 | Not measured | Only Phi 4 measured |
| LMArena Text: English | 1231 | Not measured | Only Phi 4 measured |
| LMArena Text: non-English | 1197 | Not measured | Only Phi 4 measured |
| LMArena Text: Chinese | 1212 | Not measured | Only Phi 4 measured |
| LMArena Text: German | 1222 | Not measured | Only Phi 4 measured |
| LMArena Text: Japanese | 1158 | Not measured | Only Phi 4 measured |
| LMArena Text: Korean | 1151 | Not measured | Only Phi 4 measured |
| LMArena Text: French | 1224 | Not measured | Only Phi 4 measured |
| LMArena Text: Spanish | 1234 | Not measured | Only Phi 4 measured |
| LMArena Text: Russian | 1209 | Not measured | Only Phi 4 measured |
| LMArena Text: multi-turn | 1206 | Not measured | Only Phi 4 measured |
| LMArena Text: longer queries | 1217 | Not measured | Only Phi 4 measured |
| LMArena Text: writing and language | 1198 | Not measured | Only Phi 4 measured |
| LMArena Text: entertainment and media | 1162 | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | 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
Phi 4 costs less
Repository review
50K input + 3K output tokens
Phi 4 costs less
Agent loop
200K input + 10K output tokens
Phi 4 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 | Microsoft Phi 4 | Nous Hermes 3 70B Instruct |
|---|---|---|
| Maker | Microsoft | Nous Research |
| Weights | Open weights | Open weights |
| Released | January 10, 2025 | August 18, 2024 |
| Context window | 16K | 131K |
| Input $/Mtok | $0.07 | $0.70 |
| Output $/Mtok | $0.14 | $0.70 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Phi 4 better than Hermes 3 70B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 5.0x cheaper ($0.14 vs $0.70 per million) and work measured by AA Intelligence Index or Humanity's Last Exam (Artificial Analysis run), where it leads.
Which is cheaper, Phi 4 or Hermes 3 70B Instruct?
Phi 4 costs $0.07 per million input tokens and $0.14 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, Phi 4 or Hermes 3 70B Instruct?
Hermes 3 70B Instruct, with 131K tokens against 16K.
How many benchmarks is the Phi 4 vs Hermes 3 70B Instruct comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. Phi 4's coding index rests on 0 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.