Gemma 4 31B IT vs GPT-5.6 Cyber vs Claude Mythos 5
Gemma 4 31B IT comes out ahead, 70 to 36 and 30 on our weighted score, and it is the cheaper option too.
- Our pick
GoogleGemma 4 31B IT
70/100- ECI142.8
- Price$0.14 / $0.40
- Context262K
OpenAIGPT-5.6 Cyber
30/100- ECI—
- Price$12.50 / $75.00
- Context400K
AnthropicClaude Mythos 5
36/100- ECI—
- Price$10.00 / $50.00
- Context1M
Gemma 4 31B IT is our pick
Gemma 4 31B IT is the better all-round choice, scoring 70/100 against Claude Mythos 5 (36) and GPT-5.6 Cyber (30). It leads on price. Claude Mythos 5 wins on inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGemma 4 31B ITGemma 4 31B IT $0.205 · Claude Mythos 5 $20.00 · GPT-5.6 Cyber $28.13 per 1M tokens (3:1 blend)
- Longest contextClaude Mythos 5Claude Mythos 5 1,000,000 · GPT-5.6 Cyber 400,000 · Gemma 4 31B IT 262,144 tokens
- Widest inputsClaude Mythos 5Gemma 4 31B IT: Text, Images · GPT-5.6 Cyber: Text, Images · Claude Mythos 5: Text, Images, PDFs
- Self-hostingGemma 4 31B ITPublishes downloadable weights
| Measure | Weight | Gemma 4 31B IT | GPT-5.6 Cyber | Claude Mythos 5 |
|---|---|---|---|---|
| Price | 50% | 83 | 0 | 0 |
| Inputs & features | 30% | 70 | 70 | 80 |
| Context window | 20% | 37 | 44 | 60 |
| Overall | 100% | 70/100 | 30/100 | 36/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemma 4 31B ITGoogle | GPT-5.6 CyberOpenAI | Claude Mythos 5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 142.8 | — | — |
| ECI rank | #86 of 148 | — | — |
| GPQA DiamondGraduate-level science questions | 75.8% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% | — | — |
| SimpleQA VerifiedShort factual questions | 10.4% | — | — |
| Price per million tokens | |||
| Input | $0.14 (best) | $12.50 | $10.00 |
| Output | $0.40 (best) | $75.00 | $50.00 |
| Cached input | — | $1.25 | — |
| Blended (3:1) | $0.205 (best) | $28.13 | $20.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 30 providers | Official OpenAI API | Median of 2 providers |
| Limits | |||
| Context window | 262,144 tokens | 400,000 tokens | 1,000,000 tokens (best) |
| Max output | 32,768 tokens | 128,000 tokens (best) | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeslow · medium · high · xhigh · max | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | gemma-4-31b-it | gpt-daybreak-red-latest | — |
| API providers | 38 (best) | 1 | 2 |
| Released | Apr 2, 2026 | Aug 7, 2026 | Jun 9, 2026 |
| Knowledge cutoff | — | Feb 16, 2026 | Jan 31, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemma 4 31B IT$2.20
- GPT-5.6 Cyber$275.00
- Claude Mythos 5$200.00
Which should you choose?
Which is better: Gemma 4 31B IT, GPT-5.6 Cyber or Claude Mythos 5?
Gemma 4 31B IT is the better all-round choice, scoring 70/100 against Claude Mythos 5 (36) and GPT-5.6 Cyber (30). It leads on price. Claude Mythos 5 wins on inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemma 4 31B IT, GPT-5.6 Cyber or Claude Mythos 5?
Gemma 4 31B IT is cheaper at $0.14 input / $0.40 output per million tokens (median across 30 API providers). Claude Mythos 5 costs $10.00 input / $50.00 output per million tokens (median across 2 API providers); GPT-5.6 Cyber costs $12.50 input / $75.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.205 per million tokens for Gemma 4 31B IT versus $20.00 for Claude Mythos 5 (98× as much) and $28.13 for GPT-5.6 Cyber (137× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 4 31B IT has an ECI of 142.8, GPT-5.6 Cyber has not been scored yet and Claude Mythos 5 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 4 31B IT, GPT-5.6 Cyber and Claude Mythos 5 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Claude Mythos 5 has the largest context window at 1,000,000 tokens, against 400,000 for GPT-5.6 Cyber and 262,144 for Gemma 4 31B IT. Maximum output per response: Gemma 4 31B IT up to 32,768, GPT-5.6 Cyber up to 128,000, Claude Mythos 5 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 31B IT accepts text and images; GPT-5.6 Cyber accepts text and images; Claude Mythos 5 accepts text, images and PDFs. Claude Mythos 5 handles the widest range of inputs.
Are any of these open source?
Gemma 4 31B IT publishes its weights and can be self-hosted; GPT-5.6 Cyber and Claude Mythos 5 is proprietary.
Which is newer?
GPT-5.6 Cyber is the newest, released Aug 7, 2026. Claude Mythos 5 came out Jun 9, 2026; Gemma 4 31B IT came out Apr 2, 2026. Knowledge cutoff: GPT-5.6 Cyber Feb 16, 2026, Claude Mythos 5 Jan 31, 2026.
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.
