Model comparison
GPT-3.5-turbo vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 23.2 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 6.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.2% for GPT-3.5-turbo and 90% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
- Inkling-Small accepts more context: 524K tokens versus 16K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 23.2 | 46.5 |
| Released | 2023-03-01 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 16K | 524K |
| Max output | 4K | 1.05M |
| Input $ / M tokens | $0.50 | $0.45 |
| Output $ / M tokens | $1.50 | $1.20 |
| Results tracked | 44 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
GPT-3.5-turbo: 23.9 (#331), Inkling-Small: 43.6 (#85)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Coding | 1136 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Inkling-Small: —
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Inkling-Small leads
GPT-3.5-turbo: 13.8 (#332), Inkling-Small: 38.6 (#63)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| Chess Puzzles | 0% | 18% |
| LMArena Hard Prompts | 1108 | 1423 |
| Mystery Game Puzzles | 3% | 6% |
| Epoch Capabilities Index | 118.55 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Inkling-Small leads
GPT-3.5-turbo: 6.3 (#327), Inkling-Small: 45.1 (#77)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0% | 46.3% |
| OTIS Mock AIME 2024-2025 | 2.2% | 90% |
| LMArena Math | 1142 | 1459 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Inkling-Small leads
GPT-3.5-turbo: 10.0 (#303), Inkling-Small: 48.2 (#77)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| GPQA Diamond | 28% | 88.5% |
| LMArena Expert | 1070 | 1442 |
| SimpleQA Verified | — | 19.1% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, Inkling-Small: 39.1 (#62)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
GPT-3.5-turbo: 31.5 (#258), Inkling-Small: 51.7 (#104)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1108 | 1402 |
| LMArena Chinese | 1075 | 1465 |
| LMArena French | 1118 | 1436 |
| LMArena German | 1090 | 1405 |
| LMArena Japanese | 1043 | 1405 |
| LMArena Korean | 1019 | 1363 |
| LMArena Russian | 1123 | 1391 |
| LMArena Spanish | 1121 | 1428 |
Instruction Following Inkling-Small leads
GPT-3.5-turbo: 57.9 (#262), Inkling-Small: 73.8 (#114)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1119 | 1399 |
Long Context Inkling-Small leads
GPT-3.5-turbo: 34.0 (#254), Inkling-Small: 42.7 (#118)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1121 | 1401 |
Writing & Preference Inkling-Small leads
GPT-3.5-turbo: 25.3 (#305), Inkling-Small: 59.6 (#107)
| Benchmark | GPT-3.5-turbo | Inkling-Small |
|---|---|---|
| LMArena Text | 1125 | 1414 |
| LMArena Creative Writing | 1092 | 1331 |
| EQ-Bench Creative Writing | 451 | 1491 |
| LMArena Multi-Turn | 1117 | 1418 |
Frequently asked questions
Is GPT-3.5-turbo better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 23.2 on the Noometry Index.
Which is cheaper, GPT-3.5-turbo or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.
Is GPT-3.5-turbo or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Inkling-Small share?
24 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Inkling-Small has 33.