Gemini 3 Flash Preview vs Grok 4.20 (Reasoning) vs Inkling Small
Gemini 3 Flash Preview comes out ahead, 72 to 68 and 67 on our weighted score, though Inkling Small is 29% cheaper per token.
- Our pick
GoogleGemini 3 Flash Preview
72/100- ECI152.0
- Price$0.50 / $3.00
- Context1.05M
xAIGrok 4.20 (Reasoning)
67/100- ECI152.3
- Price$1.25 / $2.50
- Context1M
Thinking MachinesInkling Small
68/100- ECI150.5
- Price$0.58 / $1.44
- Context1.05M
Gemini 3 Flash Preview is our pick
Gemini 3 Flash Preview is the better all-round choice, scoring 72/100 against Inkling Small (68) and Grok 4.20 (Reasoning) (67). It leads on inputs & features. Inkling Small wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGrok 4.20 (Reasoning)Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.3 · Gemini 3 Flash Preview 152.0 · Inkling Small 150.5
- Lowest priceInkling SmallInkling Small $0.795 · Gemini 3 Flash Preview $1.13 · Grok 4.20 (Reasoning) $1.56 per 1M tokens (3:1 blend)
- Longest contextGemini 3 Flash Preview and Inkling SmallGemini 3 Flash Preview 1,048,576 · Inkling Small 1,048,576 · Grok 4.20 (Reasoning) 1,000,000 tokens
- Widest inputsGemini 3 Flash PreviewGemini 3 Flash Preview: Text, Images, PDFs, Audio, Video · Grok 4.20 (Reasoning): Text, Images, PDFs · Inkling Small: Text, Images, Audio
- Self-hostingInkling SmallPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Gemini 3 Flash Preview | Grok 4.20 (Reasoning) | Inkling Small |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 79 | 79 | 77 |
| Price | 25% | 45 | 39 | 52 |
| Inputs & features | 15% | 100 | 80 | 70 |
| Context window | 10% | 61 | 60 | 61 |
| Overall | 100% | 72/100 | 67/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini 3 Flash PreviewGoogle | Grok 4.20 (Reasoning)xAI | Inkling SmallThinking Machines |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 152.0 | 152.3 (best) | 150.5 |
| ECI rank | #53 of 165 | #51 of 165 (best) | #58 of 165 |
| GPQA DiamondGraduate-level science questions | 89.4% (best) | 89.3% | 88.5% |
| FrontierMath Tiers 1–3Research-level mathematics | 51.2% (best) | 44.9% | 46.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 95.6% (best) | 92.2% | 90.0% |
| SWE-bench VerifiedFixing real GitHub issues | 75.4% | — | — |
| SimpleQA VerifiedShort factual questions | 66.8% (best) | 30.2% | 19.1% |
| Price per million tokens | |||
| Input | $0.50 (best) | $1.25 | $0.58 |
| Output | $3.00 | $2.50 | $1.44 (best) |
| Cached input | $0.05 (best) | $0.20 | $0.116 |
| Blended (3:1) | $1.13 | $1.56 | $0.795 (best) |
| Long-context rate | Same rate | Over 200K: $2.50 / $5.00 | Same rate |
| Price source | Official Google API | Official xAI API | Official Thinking Machines API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,000,000 tokens | 1,048,576 tokens (best) |
| Max output | 65,536 tokens | 30,000 tokens | 1,048,576 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | No |
| Audio | Yes | No | Yes |
| Video | Yes | No | No |
| Reasoning | Yesminimal · low · medium · high | Yes | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | OpenApache-2.0 |
| API model ID | gemini-3-flash-preview | grok-4.20-0309-reasoning | thinkingmachines/Inkling-Small |
| API providers | 31 (best) | 15 | 12 |
| Released | Dec 17, 2025 | Mar 9, 2026 | Jul 30, 2026 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 3 Flash Preview$11.00
- Grok 4.20 (Reasoning)$17.50
- Inkling Small$8.68
Which should you choose?
Which is better: Gemini 3 Flash Preview, Grok 4.20 (Reasoning) or Inkling Small?
Gemini 3 Flash Preview is the better all-round choice, scoring 72/100 against Inkling Small (68) and Grok 4.20 (Reasoning) (67). It leads on inputs & features. Inkling Small wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Gemini 3 Flash Preview, Grok 4.20 (Reasoning) or Inkling Small?
Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). Gemini 3 Flash Preview costs $0.50 input / $3.00 output per million tokens (official Google API price); Grok 4.20 (Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.795 per million tokens for Inkling Small versus $1.13 for Gemini 3 Flash Preview (1.4× as much) and $1.56 for Grok 4.20 (Reasoning) (2× as much).
Which scores higher on benchmarks?
Grok 4.20 (Reasoning) scores higher on the Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.3 (#51 of 165), Gemini 3 Flash Preview 152.0 (#53 of 165) and Inkling Small 150.5 (#58 of 165). The confidence ranges of the top two overlap (149.5–154.7 vs 150.6–153.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3 Flash Preview 89.4%, Grok 4.20 (Reasoning) 89.3%, Inkling Small 88.5%; FrontierMath Tiers 1–3 — Gemini 3 Flash Preview 51.2%, Inkling Small 46.3%, Grok 4.20 (Reasoning) 44.9%; OTIS Mock AIME 2024–2025 — Gemini 3 Flash Preview 95.6%, Grok 4.20 (Reasoning) 92.2%, Inkling Small 90.0%; SimpleQA Verified — Gemini 3 Flash Preview 66.8%, Grok 4.20 (Reasoning) 30.2%, Inkling Small 19.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Grok 4.20 (Reasoning) and Inkling Small yet, so there is no like-for-like coding score. On overall capability, Grok 4.20 (Reasoning) leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3 Flash Preview and Inkling Small have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Grok 4.20 (Reasoning). Maximum output per response: Gemini 3 Flash Preview up to 65,536, Grok 4.20 (Reasoning) up to 30,000, Inkling Small up to 1,048,576 tokens.
Which can read images, PDFs, audio or video?
Gemini 3 Flash Preview accepts text, images, PDFs, audio and video; Grok 4.20 (Reasoning) accepts text, images and PDFs; Inkling Small accepts text, images and audio. Gemini 3 Flash Preview handles the widest range of inputs.
Are any of these open source?
Inkling Small publishes its weights (Apache-2.0) and can be self-hosted; Gemini 3 Flash Preview and Grok 4.20 (Reasoning) is proprietary.
Which is newer?
Inkling Small is the newest, released Jul 30, 2026. Grok 4.20 (Reasoning) came out Mar 9, 2026; Gemini 3 Flash Preview came out Dec 17, 2025. Knowledge cutoff: Gemini 3 Flash Preview Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
Related comparisons
- Gemini 3 Flash Preview vs Kimi K2.5Moonshot AI · ECI 148.1
- Gemini 3 Flash Preview vs Qwen3.8 27BAlibaba (Qwen) · ECI 151.8
- Gemini 3 Flash Preview vs GLM-5.2Z.ai (Zhipu) · ECI 152.1
- Grok 4.20 (Reasoning) vs Kimi K2.6Moonshot AI · ECI 151.1
- Grok 4.20 (Reasoning) vs GLM-5.2Z.ai (Zhipu) · ECI 152.1
- Grok 4.20 (Reasoning) vs GPT-5.4 miniOpenAI · ECI 148.8
