Gemini 2.5 Flash vs Llama 4 Maverick 17B Instruct vs Qwen3 8B
Gemini 2.5 Flash comes out ahead, 74 to 59 and 49 on our weighted score, though Qwen3 8B is 2.7× cheaper per token.
Price in rating: Excluded · Include price
- Our pick
Google
Gemini 2.5 Flash
74/100- ECI140.8
- Price$0.30 / $2.50
- Context1.05M
Meta
Llama 4 Maverick 17B Instruct
59/100- ECI132.2
- Price$0.27 / $0.86
- Context1M
Alibaba (Qwen)
Qwen3 8B
49/100- ECI132.1
- Price$0.18 / $0.70
- Context33K
Gemini 2.5 Flash is our pick
Gemini 2.5 Flash is the better all-round choice, scoring 74/100 against Llama 4 Maverick 17B Instruct (59) and Qwen3 8B (49). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 2.5 FlashCapabilities Index (ECI): Gemini 2.5 Flash 140.8 · Llama 4 Maverick 17B Instruct 132.2 · Qwen3 8B 132.1
- Lowest priceQwen3 8BQwen3 8B $0.31 · Llama 4 Maverick 17B Instruct $0.417 · Gemini 2.5 Flash $0.85 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 FlashGemini 2.5 Flash 1,048,576 · Llama 4 Maverick 17B Instruct 1,000,000 · Qwen3 8B 32,768 tokens
- Widest inputsGemini 2.5 FlashGemini 2.5 Flash: Text, Images, PDFs, Audio, Video · Llama 4 Maverick 17B Instruct: Text, Images · Qwen3 8B: Text
- Self-hostingLlama 4 Maverick 17B Instruct and Qwen3 8BPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Gemini 2.5 Flash | Llama 4 Maverick 17B Instruct | Qwen3 8B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 69 | 61 | 60 |
| Inputs & features | 20% | 100 | 50 | 35 |
| Context window | 13% | 65 | 64 | 11 |
| Overall | 100% | 74/100 | 59/100 | 49/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.8 (best) | 132.2 | 132.1 |
| ECI rank | #111 of 158 (best) | #134 of 158 | #135 of 158 |
| GPQA DiamondGraduate-level science questions | — | 67.0% (best) | 56.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 20.6% | 56.1% (best) |
| Price per million tokens | |||
| Input | $0.30 | $0.27 | $0.18 (best) |
| Output | $2.50 | $0.86 | $0.70 (best) |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.85 | $0.417 | $0.31 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Google API | Median of 16 providers | Official Alibaba API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,000,000 tokens | 32,768 tokens |
| Max output | 65,536 tokens (best) | 16,384 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | OpenApache-2.0 |
| API model ID | gemini-2.5-flash | — | qwen3-8b |
| API providers | 31 (best) | 16 | 6 |
| Released | Jun 17, 2025 | Apr 5, 2025 | Apr 29, 2025 |
| Knowledge cutoff | Jan 2025 | Aug 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Gemini 2.5 Flash$8.00
Llama 4 Maverick 17B Instruct$4.42
Qwen3 8B$3.20
Which should you choose?
Which is better: Gemini 2.5 Flash, Llama 4 Maverick 17B Instruct or Qwen3 8B?
Gemini 2.5 Flash is the better all-round choice, scoring 74/100 against Llama 4 Maverick 17B Instruct (59) and Qwen3 8B (49). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 2.5 Flash, Llama 4 Maverick 17B Instruct or Qwen3 8B?
Qwen3 8B is cheaper at $0.18 input / $0.70 output per million tokens (official Alibaba API price). Llama 4 Maverick 17B Instruct costs $0.27 input / $0.86 output per million tokens (median across 16 API providers); Gemini 2.5 Flash costs $0.30 input / $2.50 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.31 per million tokens for Qwen3 8B versus $0.417 for Llama 4 Maverick 17B Instruct (1.3× as much) and $0.85 for Gemini 2.5 Flash (2.7× as much).
Which scores higher on benchmarks?
Gemini 2.5 Flash scores higher on the Capabilities Index (ECI): Gemini 2.5 Flash 140.8 (#111 of 158), Llama 4 Maverick 17B Instruct 132.2 (#134 of 158) and Qwen3 8B 132.1 (#135 of 158). Their confidence ranges do not overlap (138.4–143.1 vs 130.0–134.3), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Flash, Llama 4 Maverick 17B Instruct and Qwen3 8B yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Flash 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 2.5 Flash has the largest context window at 1,048,576 tokens, against 1,000,000 for Llama 4 Maverick 17B Instruct and 32,768 for Qwen3 8B. Maximum output per response: Gemini 2.5 Flash up to 65,536, Llama 4 Maverick 17B Instruct up to 16,384, Qwen3 8B up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Flash accepts text, images, PDFs, audio and video; Llama 4 Maverick 17B Instruct accepts text and images; Qwen3 8B accepts text. Gemini 2.5 Flash handles the widest range of inputs.
Are any of these open source?
Llama 4 Maverick 17B Instruct and Qwen3 8B publishes its weights (Apache-2.0) and can be self-hosted; Gemini 2.5 Flash is proprietary.
Which is newer?
Gemini 2.5 Flash is the newest, released Jun 17, 2025. Qwen3 8B came out Apr 29, 2025; Llama 4 Maverick 17B Instruct came out Apr 5, 2025. Knowledge cutoff: Gemini 2.5 Flash Jan 2025, Llama 4 Maverick 17B Instruct Aug 2024.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 18, 2026.