Gemini 4 Carbon vs GPT-6.1 Sol vs Claude Haiku 5.5
Claude Haiku 5.5 comes out ahead, 82 to 75 and 71 on our weighted score, and it is the cheaper option too.Gemini 4 Carbon comes out ahead, 93 to 88 and 83 on our weighted score, though Claude Haiku 5.5 is 20× cheaper per token.
Google
Gemini 4 Carbon
75/100- ECI169.7
- Price$2.00 / $10.00
- Context1.05M
OpenAI
GPT-6.1 Sol
71/100- ECI168.6
- Price$2.00 / $10.00
- Context1.05M
- Our pick
Anthropic
Claude Haiku 5.5
82/100- ECI160.3
- Price$0.10 / $0.50
- Context1M
- Our pick
Google
Gemini 4 Carbon
93/100- ECI169.7
- Price$2.00 / $10.00
- Context1.05M
OpenAI
GPT-6.1 Sol
88/100- ECI168.6
- Price$2.00 / $10.00
- Context1.05M
Anthropic
Claude Haiku 5.5
83/100- ECI160.3
- Price$0.10 / $0.50
- Context1M
Claude Haiku 5.5 is our pickGemini 4 Carbon is our pick
Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Gemini 4 Carbon (75) and GPT-6.1 Sol (71). It leads on price. Gemini 4 Carbon wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 4 Carbon is the better all-round choice, scoring 93/100 against GPT-6.1 Sol (88) and Claude Haiku 5.5 (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 4 CarbonCapabilities Index (ECI): Gemini 4 Carbon 169.7 · GPT-6.1 Sol 168.6 · Claude Haiku 5.5 160.3
- Lowest priceClaude Haiku 5.5Claude Haiku 5.5 $0.20 · Gemini 4 Carbon $4.00 · GPT-6.1 Sol $4.00 per 1M tokens (3:1 blend)
- Longest contextGPT-6.1 Sol and Gemini 4 CarbonGPT-6.1 Sol 1,050,000 · Gemini 4 Carbon 1,048,576 · Claude Haiku 5.5 1,000,000 tokens
- Widest inputsGemini 4 CarbonGemini 4 Carbon: Text, Images, PDFs, Audio, Video · GPT-6.1 Sol: Text, Images, PDFs · Claude Haiku 5.5: Text, Images, PDFs
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | Gemini 4 Carbon | GPT-6.1 Sol | Claude Haiku 5.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 97 | 96 | 88 |
| Price | 25% | 20 | 20 | 79 |
| Inputs & features | 15% | 100 | 80 | 80 |
| Context window | 10% | 65 | 65 | 64 |
| Overall | 100% | 75/100 | 71/100 | 82/100 |
| Measure | Weight | Gemini 4 Carbon | GPT-6.1 Sol | Claude Haiku 5.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 97 | 96 | 88 |
| Inputs & features | 20% | 100 | 80 | 80 |
| Context window | 13% | 65 | 65 | 64 |
| Overall | 100% | 93/100 | 88/100 | 83/100 |
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 169.7 (best) | 168.6 | 160.3 |
| ECI rank | #3 of 159 (best) | #6 of 159 | #20 of 159 |
| ECI confidence interval | 166.6–173.1 | 165.7–171.9 | 158.2–162.7 |
| ECI evaluation date | Nov 10, 2026 | Sep 29, 2026 | Oct 7, 2026 |
| Documented capabilities | Google's most capable reasoning model for complex software engineering, deep math and science, high factual accuracy, and long-horizon autonomous agents | Near-Astra performance for complex coding, computer use, and professional work at a lower cost. | Fast Claude model for responsive assistance, classification, and lightweight agents |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 96.5%high (best) | 95.4%max | 89.7%max |
| FrontierMath Tiers 1–3Research-level mathematics | 90.5%high | 93.7%max (best) | 75.1%max |
| OTIS Mock AIME 2024–2025Competition mathematics | 100%high (best) | 100%max (best) | 98.9%xhigh |
| SimpleQA VerifiedShort factual questions | 77.7%high (best) | 73.9%max | 23.8%max |
| Publisher-reported benchmarks | |||
| GDPval-AA 2.1Publisher-reported result | Not published | Not published | 1620EloReported resultOct 7, 2026 |
| AA-Briefcase 1.1Publisher-reported result | Not published | Not published | 1578EloReported resultOct 7, 2026 |
| OSWorld 2.1offline subset | Not published | Not published | 72.4partial scoreReported resultOct 7, 2026 |
| Humanity's Last Examno tools | Not published | Not published | 45.9scoreReported resultOct 7, 2026 |
| Humanity's Last Examwith tools | Not published | Not published | 57.4scoreReported resultOct 7, 2026 |
| Terminal-Bench 4.0Publisher-reported result | Not published | Not published | 39.2scoreReported resultOct 7, 2026 |
| FrontierCode 1.1 · MainPublisher-reported result | Not published | Not published | 46.4scoreReported resultOct 7, 2026 |
| Chartographyno tools | Not published | Not published | 46.4scoreReported resultOct 7, 2026 |
| Price per million tokens | |||
| Input | $2.00 | $2.00 | $0.10 (best) |
| Output | $10.00 | $10.00 | $0.50 (best) |
| Cached input | $0.10 | $0.10 | $0.01 (best) |
| Blended (3:1) | $4.00 | $4.00 | $0.20 (best) |
| Long-context rate | Same rate | Over 272K: $4.00 / $15.00 | Over 100K: $0.50 / $2.50 |
| Price source | Official Google API | Official OpenAI API | Official Anthropic API |
| Limits | |||
| Context window | 1,048,576 tokens | 1,050,000 tokens (best) | 1,000,000 tokens |
| Max input | Not published | 922,000 tokens | Not published |
| Max output | 65,536 tokens | 128,000 tokens (best) | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | Yes |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yeslow · medium · high | Yeslow · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| File attachments | Yes | Yes | Yes |
| Temperature control | Yes | No | No |
| Reasoning control | effort | effort | effort |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gemini-4-carbon | gpt-6.1-sol | claude-haiku-5-5 |
| API providers | 19 | 51 (best) | 48 |
| Released | Nov 10, 2026 | Sep 29, 2026 | Oct 7, 2026 |
| Knowledge cutoff | Mar 2026 | Apr 30, 2026 | Jun 2026 |
| Publisher documentation | Publisher documentation | Publisher documentation | Publisher documentation |
| Source metadata updated | Nov 10, 2026 | Sep 29, 2026 | Oct 7, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Gemini 4 Carbon$40.00
GPT-6.1 Sol$40.00
Claude Haiku 5.5$2.00
Which should you choose?
Which is better: Gemini 4 Carbon, GPT-6.1 Sol or Claude Haiku 5.5?
Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Gemini 4 Carbon (75) and GPT-6.1 Sol (71). It leads on price. Gemini 4 Carbon wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 4 Carbon is the better all-round choice, scoring 93/100 against GPT-6.1 Sol (88) and Claude Haiku 5.5 (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 4 Carbon, GPT-6.1 Sol or Claude Haiku 5.5?
Claude Haiku 5.5 is cheaper at $0.10 input / $0.50 output per million tokens (official Anthropic API price). Gemini 4 Carbon costs $2.00 input / $10.00 output per million tokens (official Google API price); GPT-6.1 Sol costs $2.00 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Claude Haiku 5.5 versus $4.00 for Gemini 4 Carbon (20× as much) and $4.00 for GPT-6.1 Sol (20× as much).
Which scores higher on benchmarks?
Gemini 4 Carbon scores higher on the Capabilities Index (ECI): Gemini 4 Carbon 169.7 (#3 of 159), GPT-6.1 Sol 168.6 (#6 of 159) and Claude Haiku 5.5 160.3 (#20 of 159). The confidence ranges of the top two overlap (166.6–173.1 vs 165.7–171.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 4 Carbon 96.5%, GPT-6.1 Sol 95.4%, Claude Haiku 5.5 89.7%; FrontierMath Tiers 1–3 — GPT-6.1 Sol 93.7%, Gemini 4 Carbon 90.5%, Claude Haiku 5.5 75.1%; OTIS Mock AIME 2024–2025 — Gemini 4 Carbon 100%, GPT-6.1 Sol 100%, Claude Haiku 5.5 98.9%; SimpleQA Verified — Gemini 4 Carbon 77.7%, GPT-6.1 Sol 73.9%, Claude Haiku 5.5 23.8%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 4 Carbon, GPT-6.1 Sol and Claude Haiku 5.5 yet, so there is no like-for-like coding score. On overall capability, Gemini 4 Carbon 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-6.1 Sol and Gemini 4 Carbon have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Haiku 5.5. Maximum output per response: Gemini 4 Carbon up to 65,536, GPT-6.1 Sol up to 128,000, Claude Haiku 5.5 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Gemini 4 Carbon accepts text, images, PDFs, audio and video; GPT-6.1 Sol accepts text, images and PDFs; Claude Haiku 5.5 accepts text, images and PDFs. Gemini 4 Carbon handles the widest range of inputs.
Are any of these open source?
No. Gemini 4 Carbon, GPT-6.1 Sol and Claude Haiku 5.5 are proprietary and only available through APIs and apps.
Which is newer?
Gemini 4 Carbon is the newest, released Nov 10, 2026. Claude Haiku 5.5 came out Oct 7, 2026; GPT-6.1 Sol came out Sep 29, 2026. Knowledge cutoff: Gemini 4 Carbon Mar 2026, GPT-6.1 Sol Apr 30, 2026, Claude Haiku 5.5 Jun 2026.
How do you decide the winner?
This rating uses 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 22, 2026.This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 22, 2026.