Model comparison
Inkling-Small vs Phi-4 Mini
Inkling-Small is the stronger model overall, scoring 46.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.9× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
MicrosoftSummary
- They share 2 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 25.3.
- The biggest single-benchmark swing is SciCode: 48.7% for Inkling-Small and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
Side by side
| Inkling-Small | Phi-4 Mini | |
|---|---|---|
| Provider | Thinking Machines Lab | Microsoft |
| Noometry Index | 46.5 | 30.9 |
| Released | 2026-07-15 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 524K | 128K |
| Max output | 1.05M | 4K |
| Input $ / M tokens | $0.45 | $0.075 |
| Output $ / M tokens | $1.20 | $0.30 |
| Results tracked | 33 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Phi-4 Mini: 28.1 (#317)
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| SciCode | 48.7% | 10.8% |
| LMArena WebDev | 1409 | — |
| LMArena Coding | 1451 | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Phi-4 Mini: 22.4 (#195)
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| CritPt | 8.3% | 0% |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| LMArena Hard Prompts | 1423 | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Not comparable
Inkling-Small: 45.1 (#77), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| LMArena Math | 1459 | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Phi-4 Mini: 25.3 (#262)
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Not comparable
Inkling-Small: 51.7 (#104), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1402 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1428 | — |
Instruction Following Not comparable
Inkling-Small: 73.8 (#114), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1399 | — |
Long Context Not comparable
Inkling-Small: 42.7 (#118), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1401 | — |
Writing & Preference Not comparable
Inkling-Small: 59.6 (#107), Phi-4 Mini: —
| Benchmark | Inkling-Small | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1414 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Inkling-Small better than Phi-4 Mini?
Inkling-Small is the stronger model overall, scoring 46.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.9× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Phi-4 Mini better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Inkling-Small and Phi-4 Mini share?
2 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Phi-4 Mini has 3.