DeepSeek V4 Flash 0731 vs GPT-6 Luna vs Claude Haiku 5.5
Too close to call on our weighted score (Claude Haiku 5.5 83, GPT-6 Luna 80, DeepSeek V4 Flash 0731 73). The right pick depends on what you value most.
DeepSeekDeepSeek V4 Flash 0731
73/100- ECI154.9
- Price$0.14 / $0.28
- Context1M
OpenAIGPT-6 Luna
80/100- ECI156.8
- Price$0.10 / $0.50
- Context1.05M
AnthropicClaude Haiku 5.5
83/100- ECI160.4
- Price$0.10 / $0.50
- Context1M
Too close to call
It is close. Our weighted score puts them within 2 points (Claude Haiku 5.5 83/100, GPT-6 Luna 80/100, DeepSeek V4 Flash 0731 73/100), so choose by what matters most for your work: Claude Haiku 5.5 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Haiku 5.5Capabilities Index (ECI): Claude Haiku 5.5 160.4 · GPT-6 Luna 156.8 · DeepSeek V4 Flash 0731 154.9
- Lowest priceDeepSeek V4 Flash 0731DeepSeek V4 Flash 0731 $0.175 · GPT-6 Luna $0.20 · Claude Haiku 5.5 $0.20 per 1M tokens (3:1 blend)
- Longest contextGPT-6 LunaGPT-6 Luna 1,050,000 · DeepSeek V4 Flash 0731 1,000,000 · Claude Haiku 5.5 1,000,000 tokens
- Widest inputsGPT-6 Luna and Claude Haiku 5.5DeepSeek V4 Flash 0731: Text · GPT-6 Luna: Text, Images, PDFs · Claude Haiku 5.5: Text, Images, PDFs
- Self-hostingDeepSeek V4 Flash 0731Publishes downloadable weights (MIT)
| Measure | Weight | DeepSeek V4 Flash 0731 | GPT-6 Luna | Claude Haiku 5.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 83 | 85 | 89 |
| Price | 25% | 82 | 80 | 80 |
| Inputs & features | 15% | 35 | 80 | 80 |
| Context window | 10% | 60 | 61 | 60 |
| Overall | 100% | 73/100 | 80/100 | 83/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek V4 Flash 0731DeepSeek | GPT-6 LunaOpenAI | Claude Haiku 5.5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 154.9 | 156.8 | 160.4 (best) |
| ECI rank | #41 of 165 | #28 of 165 | #14 of 165 (best) |
| GPQA DiamondGraduate-level science questions | 91.0% (best) | 90.5% | 89.7% |
| FrontierMath Tiers 1–3Research-level mathematics | 57.5% | 79.0% (best) | 75.1% |
| OTIS Mock AIME 2024–2025Competition mathematics | 94.4% | 98.9% (best) | 98.9% (best) |
| SimpleQA VerifiedShort factual questions | 33.6% | 41.4% (best) | 23.8% |
| Price per million tokens | |||
| Input | $0.14 | $0.10 (best) | $0.10 (best) |
| Output | $0.28 (best) | $0.50 | $0.50 |
| Cached input | — | $0.01 | $0.01 |
| Blended (3:1) | $0.175 (best) | $0.20 | $0.20 |
| Long-context rate | Same rate | Over 272K: $0.20 / $0.75 | Over 100K: $0.50 / $2.50 |
| Price source | Median of 51 providers | Official OpenAI API | Official Anthropic API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,050,000 tokens (best) | 1,000,000 tokens |
| Max output | 384,000 tokens (best) | 128,000 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeslow · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | Proprietary | Proprietary |
| API model ID | — | gpt-6-luna | claude-haiku-5-5 |
| API providers | 52 (best) | 35 | 33 |
| Released | Jul 31, 2026 | Sep 22, 2026 | Oct 7, 2026 |
| Knowledge cutoff | May 2025 | May 18, 2026 | Jun 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek V4 Flash 0731$1.96
- GPT-6 Luna$2.00
- Claude Haiku 5.5$2.00
Which should you choose?
Which is better: DeepSeek V4 Flash 0731, GPT-6 Luna or Claude Haiku 5.5?
It is close. Our weighted score puts them within 2 points (Claude Haiku 5.5 83/100, GPT-6 Luna 80/100, DeepSeek V4 Flash 0731 73/100), so choose by what matters most for your work: Claude Haiku 5.5 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek V4 Flash 0731, GPT-6 Luna or Claude Haiku 5.5?
DeepSeek V4 Flash 0731 is cheaper at $0.14 input / $0.28 output per million tokens (median across 51 API providers). GPT-6 Luna costs $0.10 input / $0.50 output per million tokens (official OpenAI API price); Claude Haiku 5.5 costs $0.10 input / $0.50 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for DeepSeek V4 Flash 0731 versus $0.20 for GPT-6 Luna (1.1× as much) and $0.20 for Claude Haiku 5.5 (1.1× as much).
Which scores higher on benchmarks?
Claude Haiku 5.5 scores higher on the Capabilities Index (ECI): Claude Haiku 5.5 160.4 (#14 of 165), GPT-6 Luna 156.8 (#28 of 165) and DeepSeek V4 Flash 0731 154.9 (#41 of 165). The confidence ranges of the top two overlap (157.3–163.8 vs 154.0–159.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek V4 Flash 0731 91.0%, GPT-6 Luna 90.5%, Claude Haiku 5.5 89.7%; FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, Claude Haiku 5.5 75.1%, DeepSeek V4 Flash 0731 57.5%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, Claude Haiku 5.5 98.9%, DeepSeek V4 Flash 0731 94.4%; SimpleQA Verified — GPT-6 Luna 41.4%, DeepSeek V4 Flash 0731 33.6%, Claude Haiku 5.5 23.8%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Flash 0731, GPT-6 Luna and Claude Haiku 5.5 yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 5.5 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?
GPT-6 Luna has the largest context window at 1,050,000 tokens, against 1,000,000 for DeepSeek V4 Flash 0731 and 1,000,000 for Claude Haiku 5.5. Maximum output per response: DeepSeek V4 Flash 0731 up to 384,000, GPT-6 Luna up to 128,000, Claude Haiku 5.5 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Flash 0731 accepts text; GPT-6 Luna accepts text, images and PDFs; Claude Haiku 5.5 accepts text, images and PDFs. GPT-6 Luna handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Flash 0731 publishes its weights (MIT) and can be self-hosted; GPT-6 Luna and Claude Haiku 5.5 is proprietary.
Which is newer?
Claude Haiku 5.5 is the newest, released Oct 7, 2026. GPT-6 Luna came out Sep 22, 2026; DeepSeek V4 Flash 0731 came out Jul 31, 2026. Knowledge cutoff: DeepSeek V4 Flash 0731 May 2025, GPT-6 Luna May 18, 2026, Claude Haiku 5.5 Jun 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 Nov 2, 2026.
Related comparisons
- DeepSeek V4 Flash 0731 vs GLM-5.3-FlashZ.ai (Zhipu) · ECI 153.2
- DeepSeek V4 Flash 0731 vs Gemini 3.6 FlashGoogle · ECI 154.7
- GPT-6 Luna vs GLM-5.3-FlashZ.ai (Zhipu) · ECI 153.2
- GPT-6 Luna vs Gemini 3.8 FlashGoogle · ECI 157.6
- Claude Haiku 5.5 vs DeepSeek V4.1 Flash 1017DeepSeek · ECI 158.8
- Claude Haiku 5.5 vs GLM-5.3-FlashZ.ai (Zhipu) · ECI 153.2
