# Gemini 2.5 Flash vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 3.0× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 5 categories and Inkling in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-1: 33.3% for Gemini 2.5 Flash and 79.5% for Inkling.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 39.3 | 44.1 |
| Rank | 170 | 80 |
| Context | 1.05M | 66K |
| Input $/M | $0.30 | $1.87 |
| Output $/M | $2.50 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- Inkling: 34.5 (#234)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| WeirdML | 41.9% | 32.3% |
| LMArena Coding | 1424 | 1464 |
| ALE-Bench | 661.88 | 946 |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- Inkling: 29.6 (#85)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| τ²-bench Banking | — | 25% |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- Inkling: 40.4 (#56)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| ARC-AGI-2 | 2.5% | 36.5% |
| SimpleBench | 41.2% | 50% |
| ARC-AGI-1 | 33.3% | 79.5% |
| CritPt | 1.1% | 5.4% |
| LMArena Hard Prompts | 1422 | 1451 |
| DTBench | 76.5% | 87.5% |
| LMCA | 27.5% | 37.6% |
| Epoch Capabilities Index | 143.03 | 148.54 |
| Kagi LLM Benchmark | 56.8% | — |
| Chess Puzzles | — | 21% |
| EnigmaEval | 2.7% | — |
| ForecastBench | 60.6 | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- Inkling: 31.3 (#225)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 88.9% |
| LMArena Math | 1415 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- Inkling: 55.1 (#49)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Expert | 1426 | 1465 |
| GPQA Diamond | — | 88.3% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 40.3% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- Inkling: —

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- Inkling: 54.0 (#52)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Non-English | 1409 | 1434 |
| LMArena Chinese | 1450 | 1490 |
| LMArena French | 1433 | 1458 |
| LMArena German | 1418 | 1446 |
| LMArena Japanese | 1405 | 1429 |
| LMArena Korean | 1385 | 1404 |
| LMArena Russian | 1415 | 1429 |
| LMArena Spanish | 1421 | 1448 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- Inkling: 75.1 (#71)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Instruction Following | 1405 | 1426 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- Inkling: 43.8 (#86)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Longer Query | 1419 | 1434 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- Inkling: 65.2 (#51)

| Benchmark | Gemini 2.5 Flash | Inkling |
|---|---|---|
| LMArena Text | 1417 | 1441 |
| LMArena Creative Writing | 1400 | 1387 |
| EQ-Bench Creative Writing | 1137 | 1611 |
| LMArena Multi-Turn | 1408 | 1436 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Gemini 2.5 Flash better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 3.0× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash or Inkling?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Gemini 2.5 Flash or Inkling better for coding?

Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 66K.

### How many benchmarks do Gemini 2.5 Flash and Inkling share?

28 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Inkling has 41.