Model comparison
GPT-5 Nano vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 33.5 on the Noometry Index. GPT-5 Nano costs 4.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and Inkling-Small in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 16.3.
- The biggest single-benchmark swing is ARC-AGI-1: 20.7% for GPT-5 Nano and 84% for Inkling-Small.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 400K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 33.5 | 46.5 |
| Released | 2025-08-07 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 400K | 524K |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $0.05 | $0.45 |
| Output $ / M tokens | $0.40 | $1.20 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
GPT-5 Nano: 33.6 (#254), Inkling-Small: 43.6 (#85)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Coding | 1351 | 1451 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Inkling-Small: —
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Inkling-Small leads
GPT-5 Nano: 16.3 (#306), Inkling-Small: 38.6 (#63)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 2.6% | 40.1% |
| ARC-AGI-1 | 20.7% | 84% |
| Chess Puzzles | 27% | 18% |
| LMArena Hard Prompts | 1328 | 1423 |
| Mystery Game Puzzles | 9% | 6% |
| Epoch Capabilities Index | 139.38 | 150.15 |
| Kagi LLM Benchmark | 62.2% | — |
| CritPt | — | 8.3% |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |
Math Inkling-Small leads
GPT-5 Nano: 29.4 (#241), Inkling-Small: 45.1 (#77)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | 46.3% |
| FrontierMath Tier 4 | 2.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 81.1% | 90% |
| ProofBench | 12% | 6% |
| LMArena Math | 1317 | 1459 |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Inkling-Small leads
GPT-5 Nano: 35.9 (#178), Inkling-Small: 48.2 (#77)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| GPQA Diamond | 69.4% | 88.5% |
| SimpleQA Verified | 11.7% | 19.1% |
| LMArena Expert | 1321 | 1442 |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Inkling-Small leads
GPT-5 Nano: 31.3 (#108), Inkling-Small: 39.1 (#62)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Vision | 1159 | 1235 |
| VPCT | 37.2% | — |
Multilingual Inkling-Small leads
GPT-5 Nano: 45.3 (#172), Inkling-Small: 51.7 (#104)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1313 | 1402 |
| LMArena Chinese | 1356 | 1465 |
| LMArena German | 1327 | 1405 |
| LMArena Japanese | 1226 | 1405 |
| LMArena Korean | 1269 | 1363 |
| LMArena Russian | 1296 | 1391 |
| LMArena Spanish | 1360 | 1428 |
| LMArena French | — | 1436 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Inkling-Small: 73.8 (#114)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1306 | 1399 |
| IFEval | 93.2% | — |
Long Context Inkling-Small leads
GPT-5 Nano: 31.3 (#281), Inkling-Small: 42.7 (#118)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1312 | 1401 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Inkling-Small leads
GPT-5 Nano: 39.1 (#249), Inkling-Small: 59.6 (#107)
| Benchmark | GPT-5 Nano | Inkling-Small |
|---|---|---|
| LMArena Text | 1320 | 1414 |
| LMArena Creative Writing | 1249 | 1331 |
| EQ-Bench Creative Writing | 705 | 1491 |
| LMArena Multi-Turn | 1311 | 1418 |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 33.5 on the Noometry Index. GPT-5 Nano costs 4.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Inkling-Small?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is GPT-5 Nano or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 400K.
How many benchmarks do GPT-5 Nano and Inkling-Small share?
29 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Inkling-Small has 33.