Model comparison
Gemini 2.0 Flash (Feb 2025) vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 35.1 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 15.2.
- The biggest single-benchmark swing is ARC-AGI-2: 1.3% for Gemini 2.0 Flash (Feb 2025) and 40.1% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | |
| Noometry Index | 35.1 | 46.5 |
| Released | 2024-12-06 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | — | 524K |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $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 2.0 Flash (Feb 2025): 28.4 (#315), Inkling-Small: 43.6 (#85)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Coding | 1350 | 1451 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Inkling-Small: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Inkling-Small: 38.6 (#63)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 1.3% | 40.1% |
| LMArena Hard Prompts | 1346 | 1423 |
| Epoch Capabilities Index | 135.36 | 150.15 |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LiveBench | 66.9% | — |
Math Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Inkling-Small: 45.1 (#77)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 90% |
| LMArena Math | 1352 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Inkling-Small: 48.2 (#77)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| GPQA Diamond | 64.1% | 88.5% |
| LMArena Expert | 1339 | 1442 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Inkling-Small: 39.1 (#62)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Vision | 1158 | 1235 |
| GeoBench | 77% | — |
Multilingual Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Inkling-Small: 51.7 (#104)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1342 | 1402 |
| LMArena Chinese | 1373 | 1465 |
| LMArena French | 1391 | 1436 |
| LMArena German | 1353 | 1405 |
| LMArena Japanese | 1294 | 1405 |
| LMArena Korean | 1313 | 1363 |
| LMArena Russian | 1351 | 1391 |
| LMArena Spanish | 1363 | 1428 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Inkling-Small: 73.8 (#114)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1336 | 1399 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Inkling-Small: 42.7 (#118)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1344 | 1401 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Inkling-Small leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Inkling-Small: 59.6 (#107)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Inkling-Small |
|---|---|---|
| LMArena Text | 1354 | 1414 |
| LMArena Creative Writing | 1340 | 1331 |
| EQ-Bench Creative Writing | 1128 | 1491 |
| LMArena Multi-Turn | 1350 | 1418 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Inkling-Small share?
23 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Inkling-Small has 33.