Model comparison
Inkling-Small vs Phi 3 Mini 4k Instruct
Inkling-Small is the stronger model overall, scoring 46.5 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling-Small leads 59.6 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 18% for Inkling-Small and 0% for Phi 3 Mini 4k Instruct.
Side by side
| Inkling-Small | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Thinking Machines Lab | Microsoft |
| Noometry Index | 46.5 | 27.9 |
| Released | 2026-07-15 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 524K | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 35 |
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 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1451 | 1093 |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| LMArena Hard Prompts | 1423 | 1072 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 6% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 150.15 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1459 | 1111 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 15.7% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1442 | 1045 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Phi 3 Mini 4k Instruct: —
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1402 | 1021 |
| LMArena Chinese | 1465 | 1021 |
| LMArena French | 1436 | 1076 |
| LMArena German | 1405 | 1044 |
| LMArena Japanese | 1405 | 935 |
| LMArena Korean | 1363 | 905 |
| LMArena Russian | 1391 | 1022 |
| LMArena Spanish | 1428 | 1085 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1399 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1401 | 1044 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Inkling-Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1414 | 1073 |
| LMArena Creative Writing | 1331 | 1037 |
| LMArena Multi-Turn | 1418 | 1018 |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Inkling-Small better than Phi 3 Mini 4k Instruct?
Inkling-Small is the stronger model overall, scoring 46.5 to 27.9 on the Noometry Index.
Is Inkling-Small or Phi 3 Mini 4k Instruct better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 26.6 in the Noometry coding category.
How many benchmarks do Inkling-Small and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.