Qwen3 30B-A3B Instruct 2507 vs Claude Haiku 4.5 vs GPT OSS 20B
Too close to call on our weighted score (GPT OSS 20B 61, Qwen3 30B-A3B Instruct 2507 59, Claude Haiku 4.5 57). The right pick depends on what you value most.
Alibaba (Qwen)Qwen3 30B-A3B Instruct 2507
59/100- ECI137.3
- Price$0.10 / $0.30
- Context262K
AnthropicClaude Haiku 4.5
57/100- ECI142.2
- Price$1.00 / $5.00
- Context200K
OpenAIGPT OSS 20B
61/100- ECI137.8
- Price$0.07 / $0.25
- Context131K
Too close to call
It is close. Our weighted score puts them within 2 points (GPT OSS 20B 61/100, Qwen3 30B-A3B Instruct 2507 59/100, Claude Haiku 4.5 57/100), so choose by what matters most for your work: Claude Haiku 4.5 for raw capability, GPT OSS 20B on price and Qwen3 30B-A3B Instruct 2507 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Haiku 4.5Capabilities Index (ECI): Claude Haiku 4.5 142.2 · GPT OSS 20B 137.8 · Qwen3 30B-A3B Instruct 2507 137.3
- Lowest priceGPT OSS 20BGPT OSS 20B $0.115 · Qwen3 30B-A3B Instruct 2507 $0.15 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
- Longest contextQwen3 30B-A3B Instruct 2507Qwen3 30B-A3B Instruct 2507 262,144 · Claude Haiku 4.5 200,000 · GPT OSS 20B 131,072 tokens
- Widest inputsClaude Haiku 4.5Qwen3 30B-A3B Instruct 2507: Text · Claude Haiku 4.5: Text, Images, PDFs · GPT OSS 20B: Text
- Self-hostingQwen3 30B-A3B Instruct 2507 and GPT OSS 20BPublishes downloadable weights (Apache 2.0)
| Measure | Weight | Qwen3 30B-A3B Instruct 2507 | Claude Haiku 4.5 | GPT OSS 20B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 61 | 67 | 61 |
| Price | 25% | 85 | 34 | 90 |
| Inputs & features | 15% | 25 | 80 | 35 |
| Context window | 10% | 37 | 32 | 25 |
| Overall | 100% | 59/100 | 57/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3 30B-A3B Instruct 2507Alibaba (Qwen) | Claude Haiku 4.5Anthropic | GPT OSS 20BOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 137.3 | 142.2 (best) | 137.8 |
| ECI rank | #124 of 165 | #102 of 165 (best) | #122 of 165 |
| GPQA DiamondGraduate-level science questions | 55.6% | 71.2% (best) | 60.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 62.2% | 66.7% (best) | 65.3% |
| SimpleQA VerifiedShort factual questions | — | 13.2% | — |
| Price per million tokens | |||
| Input | $0.10 | $1.00 | $0.07 (best) |
| Output | $0.30 | $5.00 | $0.25 (best) |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $0.15 | $2.00 | $0.115 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Official Anthropic API | Median of 37 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 200,000 tokens | 131,072 tokens |
| Max output | 16,384 tokens | 64,000 tokens (best) | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache 2.0 | Proprietary | Open |
| API model ID | — | claude-haiku-4-5 | — |
| API providers | 14 | 48 (best) | 41 |
| Released | Jul 28, 2025 | Oct 15, 2025 | Aug 5, 2025 |
| Knowledge cutoff | — | Feb 28, 2025 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3 30B-A3B Instruct 2507$1.60
- Claude Haiku 4.5$20.00
- GPT OSS 20B$1.20
Which should you choose?
Which is better: Qwen3 30B-A3B Instruct 2507, Claude Haiku 4.5 or GPT OSS 20B?
It is close. Our weighted score puts them within 2 points (GPT OSS 20B 61/100, Qwen3 30B-A3B Instruct 2507 59/100, Claude Haiku 4.5 57/100), so choose by what matters most for your work: Claude Haiku 4.5 for raw capability, GPT OSS 20B on price and Qwen3 30B-A3B Instruct 2507 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3 30B-A3B Instruct 2507, Claude Haiku 4.5 or GPT OSS 20B?
GPT OSS 20B is cheaper at $0.07 input / $0.25 output per million tokens (median across 37 API providers). Qwen3 30B-A3B Instruct 2507 costs $0.10 input / $0.30 output per million tokens (median across 12 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 $0.115 per million tokens for GPT OSS 20B versus $0.15 for Qwen3 30B-A3B Instruct 2507 (1.3× as much) and $2.00 for Claude Haiku 4.5 (17× as much).
Which scores higher on benchmarks?
Claude Haiku 4.5 scores higher on the Capabilities Index (ECI): Claude Haiku 4.5 142.2 (#102 of 165), GPT OSS 20B 137.8 (#122 of 165) and Qwen3 30B-A3B Instruct 2507 137.3 (#124 of 165). The confidence ranges of the top two overlap (139.4–143.9 vs 133.1–139.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — Claude Haiku 4.5 71.2%, GPT OSS 20B 60.8%, Qwen3 30B-A3B Instruct 2507 55.6%; OTIS Mock AIME 2024–2025 — Claude Haiku 4.5 66.7%, GPT OSS 20B 65.3%, Qwen3 30B-A3B Instruct 2507 62.2%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 30B-A3B Instruct 2507, Claude Haiku 4.5 and GPT OSS 20B yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 4.5 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?
Qwen3 30B-A3B Instruct 2507 has the largest context window at 262,144 tokens, against 200,000 for Claude Haiku 4.5 and 131,072 for GPT OSS 20B. Maximum output per response: Qwen3 30B-A3B Instruct 2507 up to 16,384, Claude Haiku 4.5 up to 64,000, GPT OSS 20B up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Qwen3 30B-A3B Instruct 2507 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; GPT OSS 20B accepts text. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
Qwen3 30B-A3B Instruct 2507 and GPT OSS 20B publishes its weights (Apache 2.0) and can be self-hosted; Claude Haiku 4.5 is proprietary.
Which is newer?
Claude Haiku 4.5 is the newest, released Oct 15, 2025. GPT OSS 20B came out Aug 5, 2025; Qwen3 30B-A3B Instruct 2507 came out Jul 28, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, GPT OSS 20B Jun 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
- Qwen3 30B-A3B Instruct 2507 vs Gemini 2.5 Flash-Lite Preview 06-17Google · ECI 133.8
- Qwen3 30B-A3B Instruct 2507 vs DeepSeek-V3.1DeepSeek · ECI 139.8
- Qwen3 30B-A3B Instruct 2507 vs Llama 4 Maverick 17B InstructMeta · ECI 132.3
- 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
- Claude Haiku 4.5 vs Qwen3 235B-A22B Thinking 2507Alibaba (Qwen) · ECI 143.8
