Model comparison
Gemini 2.5 Flash vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 39.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 4 categories and Inkling-Small in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-1: 33.3% for Gemini 2.5 Flash and 84% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 39.3 | 46.5 |
| Released | 2025-04-17 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 524K |
| Max output | 66K | 1.05M |
| Input $ / M tokens | $0.30 | $0.45 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 54 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Gemini 2.5 Flash: 35.8 (#220), Inkling-Small: 43.6 (#85)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Coding | 1424 | 1451 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Inkling-Small: —
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Inkling-Small leads
Gemini 2.5 Flash: 18.1 (#286), Inkling-Small: 38.6 (#63)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 2.5% | 40.1% |
| ARC-AGI-1 | 33.3% | 84% |
| CritPt | 1.1% | 8.3% |
| LMArena Hard Prompts | 1422 | 1423 |
| Epoch Capabilities Index | 143.03 | 150.15 |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| Chess Puzzles | — | 18% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| ForecastBench | 60.6 | — |
Math Inkling-Small leads
Gemini 2.5 Flash: 39.9 (#98), Inkling-Small: 45.1 (#77)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 90% |
| LMArena Math | 1415 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Inkling-Small leads
Gemini 2.5 Flash: 36.4 (#168), Inkling-Small: 48.2 (#77)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Expert | 1426 | 1442 |
| GPQA Diamond | — | 88.5% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Gemini 2.5 Flash leads
Gemini 2.5 Flash: 41.8 (#32), Inkling-Small: 39.1 (#62)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Vision | 1253 | 1235 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.3 (#88), Inkling-Small: 51.7 (#104)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1409 | 1402 |
| LMArena Chinese | 1450 | 1465 |
| LMArena French | 1433 | 1436 |
| LMArena German | 1418 | 1405 |
| LMArena Japanese | 1405 | 1405 |
| LMArena Korean | 1385 | 1363 |
| LMArena Russian | 1415 | 1391 |
| LMArena Spanish | 1421 | 1428 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), Inkling-Small: 73.8 (#114)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1405 | 1399 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Inkling-Small: 42.7 (#118)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1419 | 1401 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Inkling-Small leads
Gemini 2.5 Flash: 53.8 (#157), Inkling-Small: 59.6 (#107)
| Benchmark | Gemini 2.5 Flash | Inkling-Small |
|---|---|---|
| LMArena Text | 1417 | 1414 |
| LMArena Creative Writing | 1400 | 1331 |
| EQ-Bench Creative Writing | 1137 | 1491 |
| LMArena Multi-Turn | 1408 | 1418 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 39.3 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 524K.
How many benchmarks do Gemini 2.5 Flash and Inkling-Small share?
24 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Inkling-Small has 33.