Model comparison
GPT-5.4 nano vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GPT-5.4 nano scores higher in 0 categories and Inkling-Small in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 23.7.
- The biggest single-benchmark swing is ARC-AGI-2: 5.7% for GPT-5.4 nano and 40.1% for Inkling-Small.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 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-5.4 nano | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 41.9 | 46.5 |
| Released | 2026-03-17 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 400K | 524K |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $0.20 | $0.45 |
| Output $ / M tokens | $1.25 | $1.20 |
| Results tracked | 40 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5.4 nano: 43.6 (#84), Inkling-Small: 43.6 (#85)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| SciCode | 46.9% | 48.7% |
| LMArena Coding | 1405 | 1451 |
| LMArena WebDev | — | 1409 |
| WeirdML | 49.2% | — |
| ALE-Bench | 1,005 | — |
Reasoning Inkling-Small leads
GPT-5.4 nano: 23.7 (#173), Inkling-Small: 38.6 (#63)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 5.7% | 40.1% |
| ARC-AGI-1 | 51.5% | 84% |
| CritPt | 9.3% | 8.3% |
| Chess Puzzles | 30% | 18% |
| LMArena Hard Prompts | 1381 | 1423 |
| Mystery Game Puzzles | 9% | 6% |
| Epoch Capabilities Index | 145.81 | 150.15 |
| Kagi LLM Benchmark | 39.7% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| ForecastBench | 57.3 | — |
Math Inkling-Small leads
GPT-5.4 nano: 40.9 (#88), Inkling-Small: 45.1 (#77)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 46.3% |
| FrontierMath Tier 4 | 12.2% | 17.1% |
| OTIS Mock AIME 2024-2025 | 87.8% | 90% |
| ProofBench | 5% | 6% |
| LMArena Math | 1406 | 1459 |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Inkling-Small leads
GPT-5.4 nano: 41.9 (#103), Inkling-Small: 48.2 (#77)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| GPQA Diamond | 78.5% | 88.5% |
| SimpleQA Verified | 11.7% | 19.1% |
| LMArena Expert | 1396 | 1442 |
| Vectara Hallucination Rate | 3.1% | — |
Multimodal Inkling-Small leads
GPT-5.4 nano: 36.7 (#78), Inkling-Small: 39.1 (#62)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Vision | 1196 | 1235 |
Multilingual Inkling-Small leads
GPT-5.4 nano: 48.6 (#140), Inkling-Small: 51.7 (#104)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1359 | 1402 |
| LMArena Chinese | 1392 | 1465 |
| LMArena French | 1396 | 1436 |
| LMArena German | 1367 | 1405 |
| LMArena Japanese | 1343 | 1405 |
| LMArena Korean | 1320 | 1363 |
| LMArena Russian | 1363 | 1391 |
| LMArena Spanish | 1371 | 1428 |
Instruction Following Inkling-Small leads
GPT-5.4 nano: 71.9 (#144), Inkling-Small: 73.8 (#114)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1362 | 1399 |
Long Context Inkling-Small leads
GPT-5.4 nano: 41.6 (#137), Inkling-Small: 42.7 (#118)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1366 | 1401 |
Writing & Preference Inkling-Small leads
GPT-5.4 nano: 55.7 (#142), Inkling-Small: 59.6 (#107)
| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Text | 1372 | 1414 |
| LMArena Creative Writing | 1314 | 1331 |
| LMArena Multi-Turn | 1382 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
Frequently asked questions
Is GPT-5.4 nano better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or Inkling-Small?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is GPT-5.4 nano or Inkling-Small better for coding?
They score almost the same on coding (43.6 vs 43.6); test both on your own repository before choosing.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 400K.
How many benchmarks do GPT-5.4 nano and Inkling-Small share?
31 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Inkling-Small has 33.