GPT-5.4 nano vs Gemma 3 27B IT vs MiniMax-M2.7
GPT-5.4 nano comes out ahead, 68 to 61 and 60 on our weighted score, though Gemma 3 27B IT is 4.2× cheaper per token.
- Our pick
OpenAI
GPT-5.4 nano
68/100- ECI145.8
- Price$0.20 / $1.25
- Context400K
Google
Gemma 3 27B IT
60/100- ECI130.0
- Price$0.08 / $0.20
- Context131K
MiniMax
MiniMax-M2.7
61/100- ECI145.9
- Price$0.30 / $1.20
- Context205K
GPT-5.4 nano is our pick
GPT-5.4 nano is the better all-round choice, scoring 68/100 against MiniMax-M2.7 (61) and Gemma 3 27B IT (60). It leads on inputs & features and context window. Gemma 3 27B IT wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityMiniMax-M2.7Capabilities Index (ECI): MiniMax-M2.7 145.9 · GPT-5.4 nano 145.8 · Gemma 3 27B IT 130.0
- Lowest priceGemma 3 27B ITGemma 3 27B IT $0.11 · GPT-5.4 nano $0.463 · MiniMax-M2.7 $0.525 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 nanoGPT-5.4 nano 400,000 · MiniMax-M2.7 204,800 · Gemma 3 27B IT 131,072 tokens
- Widest inputsGPT-5.4 nano and Gemma 3 27B ITGPT-5.4 nano: Text, Images · Gemma 3 27B IT: Text, Images · MiniMax-M2.7: Text
- Self-hostingGemma 3 27B IT and MiniMax-M2.7Publishes downloadable weights
| Measure | Weight | GPT-5.4 nano | Gemma 3 27B IT | MiniMax-M2.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 53 | 73 |
| Price | 25% | 66 | 95 | 63 |
| Inputs & features | 15% | 70 | 50 | 35 |
| Context window | 10% | 44 | 24 | 32 |
| Overall | 100% | 68/100 | 60/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 145.8 | 130.0 | 145.9 (best) |
| ECI rank | #75 of 148 | #125 of 148 | #73 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 78.5% (best) | 47.7% | — |
| FrontierMath Tiers 1–3Research-level mathematics | 44.9% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 87.8% (best) | 22.5% | — |
| SimpleQA VerifiedShort factual questions | 11.7% | — | — |
| Price per million tokens | |||
| Input | $0.20 | $0.08 (best) | $0.30 |
| Output | $1.25 | $0.20 (best) | $1.20 |
| Cached input | $0.02 (best) | — | $0.06 |
| Blended (3:1) | $0.463 | $0.11 (best) | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 9 providers | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 400,000 tokens (best) | 131,072 tokens | 204,800 tokens |
| Max output | 128,000 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gpt-5.4-nano | — | MiniMax-M2.7 |
| API providers | 26 | 10 | 29 (best) |
| Released | Mar 17, 2026 | Mar 12, 2025 | Mar 18, 2026 |
| Knowledge cutoff | Aug 31, 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.
GPT-5.4 nano$4.50
Gemma 3 27B IT$1.20
MiniMax-M2.7$5.40
Which should you choose?
Which is better: GPT-5.4 nano, Gemma 3 27B IT or MiniMax-M2.7?
GPT-5.4 nano is the better all-round choice, scoring 68/100 against MiniMax-M2.7 (61) and Gemma 3 27B IT (60). It leads on inputs & features and context window. Gemma 3 27B IT wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.4 nano, Gemma 3 27B IT or MiniMax-M2.7?
Gemma 3 27B IT is cheaper at $0.08 input / $0.20 output per million tokens (median across 9 API providers). GPT-5.4 nano costs $0.20 input / $1.25 output per million tokens (official OpenAI API price); MiniMax-M2.7 costs $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). At a typical mix of three input tokens to one output token, that is $0.11 per million tokens for Gemma 3 27B IT versus $0.463 for GPT-5.4 nano (4.2× as much) and $0.525 for MiniMax-M2.7 (4.8× as much).
Which scores higher on benchmarks?
MiniMax-M2.7 scores higher on the Capabilities Index (ECI): MiniMax-M2.7 145.9 (#73 of 148), GPT-5.4 nano 145.8 (#75 of 148) and Gemma 3 27B IT 130.0 (#125 of 148). The confidence ranges of the top two overlap (138.2–148.0 vs 143.2–147.7), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5.4 nano, Gemma 3 27B IT and MiniMax-M2.7 yet, so there is no like-for-like coding score. On overall capability, MiniMax-M2.7 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?
GPT-5.4 nano has the largest context window at 400,000 tokens, against 204,800 for MiniMax-M2.7 and 131,072 for Gemma 3 27B IT. Maximum output per response: GPT-5.4 nano up to 128,000, Gemma 3 27B IT up to 131,072, MiniMax-M2.7 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GPT-5.4 nano accepts text and images; Gemma 3 27B IT accepts text and images; MiniMax-M2.7 accepts text. GPT-5.4 nano handles the widest range of inputs.
Are any of these open source?
Gemma 3 27B IT and MiniMax-M2.7 publishes its weights and can be self-hosted; GPT-5.4 nano is proprietary.
Which is newer?
MiniMax-M2.7 is the newest, released Mar 18, 2026. GPT-5.4 nano came out Mar 17, 2026; Gemma 3 27B IT came out Mar 12, 2025. Knowledge cutoff: GPT-5.4 nano Aug 31, 2025, Gemma 3 27B IT Aug 2024.
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 Oct 4, 2026.