Gemma 4 31B IT vs Claude Haiku 4.5 vs Seed-OSS-36B-Instruct
Too close to call on our weighted score (Gemma 4 31B IT 69, Claude Haiku 4.5 66, Seed-OSS-36B-Instruct 60). The right pick depends on what you value most.
GoogleGemma 4 31B IT
69/100- ECI143.1
- Price$0.14 / $0.40
- Context262K
AnthropicClaude Haiku 4.5
66/100- ECI142.2
- Price$1.00 / $5.00
- Context200K
ByteDance SeedSeed-OSS-36B-Instruct
60/100- ECI—
- Price—
- Context524K
Too close to call
It is close. Our weighted score puts them within 2 points (Gemma 4 31B IT 69/100, Claude Haiku 4.5 66/100, Seed-OSS-36B-Instruct 60/100), so choose by what matters most for your work: Gemma 4 31B IT for raw capability and Seed-OSS-36B-Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed-OSS-36B-Instruct has no Capabilities Index score yet.
- CapabilityGemma 4 31B ITShared benchmarks: Gemma 4 31B IT 74.5% · Seed-OSS-36B-Instruct 69.5% · Claude Haiku 4.5 68.9%
- Lowest priceGemma 4 31B ITGemma 4 31B IT $0.205 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend) · Seed-OSS-36B-Instruct unpriced
- Longest contextSeed-OSS-36B-InstructSeed-OSS-36B-Instruct 524,288 · Gemma 4 31B IT 262,144 · Claude Haiku 4.5 200,000 tokens
- Widest inputsClaude Haiku 4.5Gemma 4 31B IT: Text, Images · Claude Haiku 4.5: Text, Images, PDFs · Seed-OSS-36B-Instruct: Text
- Self-hostingGemma 4 31B IT and Seed-OSS-36B-InstructPublishes downloadable weights (Apache 2.0)
| Measure | Weight | Gemma 4 31B IT | Claude Haiku 4.5 | Seed-OSS-36B-Instruct |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 75 | 69 | 70 |
| Inputs & features | 20% | 70 | 80 | 35 |
| Context window | 13% | 37 | 32 | 49 |
| Overall | 100% | 69/100 | 66/100 | 60/100 |
Left out because at least one model lacks the data: price. 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 | Claude Haiku 4.5Anthropic | Seed-OSS-36B-InstructByteDance Seed |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 143.1 (best) | 142.2 | — |
| ECI rank | #96 of 165 (best) | #102 of 165 | — |
| GPQA DiamondGraduate-level science questions | 75.8% (best) | 71.2% | 71.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% (best) | 66.7% | 67.5% |
| SimpleQA VerifiedShort factual questions | 10.4% | 13.2% (best) | — |
| Price per million tokens | |||
| Input | $0.14 (best) | $1.00 | — |
| Output | $0.40 (best) | $5.00 | — |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $0.205 (best) | $2.00 | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Median of 36 providers | Official Anthropic API | — |
| Limits | |||
| Context window | 262,144 tokens | 200,000 tokens | 524,288 tokens (best) |
| Max output | 32,768 tokens | 64,000 tokens | 524,288 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | OpenApache 2.0 |
| API model ID | gemma-4-31b-it | claude-haiku-4-5 | — |
| API providers | 46 | 48 (best) | — |
| Released | Apr 2, 2026 | Oct 15, 2025 | Aug 20, 2025 |
| Knowledge cutoff | Jan 2025 | Feb 28, 2025 | Jul 2024 |
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
- Claude Haiku 4.5$20.00
- Seed-OSS-36B-Instruct—
Which should you choose?
Which is better: Gemma 4 31B IT, Claude Haiku 4.5 or Seed-OSS-36B-Instruct?
It is close. Our weighted score puts them within 2 points (Gemma 4 31B IT 69/100, Claude Haiku 4.5 66/100, Seed-OSS-36B-Instruct 60/100), so choose by what matters most for your work: Gemma 4 31B IT for raw capability and Seed-OSS-36B-Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed-OSS-36B-Instruct has no Capabilities Index score yet.
Which is cheaper, Gemma 4 31B IT, Claude Haiku 4.5 or Seed-OSS-36B-Instruct?
Gemma 4 31B IT is cheaper at $0.14 input / $0.40 output per million tokens (median across 36 API providers). Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic 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 $2.00 for Claude Haiku 4.5 (9.8× as much). Seed-OSS-36B-Instruct has no published per-token price.
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Gemma 4 31B IT 74.5%, Seed-OSS-36B-Instruct 69.5% and Claude Haiku 4.5 68.9%. On individual benchmarks: GPQA Diamond — Gemma 4 31B IT 75.8%, Seed-OSS-36B-Instruct 71.5%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Gemma 4 31B IT 73.3%, Seed-OSS-36B-Instruct 67.5%, Claude Haiku 4.5 66.7%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 4 31B IT, Claude Haiku 4.5 and Seed-OSS-36B-Instruct yet, so there is no like-for-like coding score. On overall capability, Gemma 4 31B IT 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?
Seed-OSS-36B-Instruct has the largest context window at 524,288 tokens, against 262,144 for Gemma 4 31B IT and 200,000 for Claude Haiku 4.5. Maximum output per response: Gemma 4 31B IT up to 32,768, Claude Haiku 4.5 up to 64,000, Seed-OSS-36B-Instruct up to 524,288 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 31B IT accepts text and images; Claude Haiku 4.5 accepts text, images and PDFs; Seed-OSS-36B-Instruct accepts text. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
Gemma 4 31B IT and Seed-OSS-36B-Instruct publishes its weights (Apache 2.0) and can be self-hosted; Claude Haiku 4.5 is proprietary.
Which is newer?
Gemma 4 31B IT is the newest, released Apr 2, 2026. Claude Haiku 4.5 came out Oct 15, 2025; Seed-OSS-36B-Instruct came out Aug 20, 2025. Knowledge cutoff: Gemma 4 31B IT Jan 2025, Claude Haiku 4.5 Feb 28, 2025, Seed-OSS-36B-Instruct Jul 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 Nov 2, 2026.
Related comparisons
- Gemma 4 31B IT vs Qwen3.5 FlashAlibaba (Qwen) · ECI 143.6
- Gemma 4 31B IT vs DeepSeek V4 FlashDeepSeek · ECI 146.2
- Gemma 4 31B IT vs GPT-5.4 nanoOpenAI · ECI 146.1
- Gemma 4 31B IT vs MiniMax-M3MiniMax · ECI 146.9
- Claude Haiku 4.5 vs GLM-4.7Z.ai (Zhipu) · ECI 143.7
- Claude Haiku 4.5 vs Mistral Medium 3.5Mistral AI · ECI 141.5
