Gemini 4 Carbon vs GPT-6 Astra
Hard reasoning: quality vs price
Compared models are ringed; the other 213 ranked here are greyed.
Lower price is better. Pareto frontier: Gemma 4 E4B, Sarvam 30B, Qwen3.5 4B, Sarvam 105B, gpt-oss-20b, Ling-3.0-flash-VL, MiMo-V2.5, Ternary Bonsai 2 27B, Claude Haiku 5.5, MiniMax-M3.1-Flash, MiMo-V2.6-Pro, GPT-6.1 Terra, Claude Sonnet 5.5, Gemini 4 Carbon. 66 models are not plotted: Muse Wonder Full, Muse Spark Open, Beam 1.0 501B A23B, DeepSeek V4.1 Flash NVFP4, GLM-5.3 Flash NVFP4, GLM-5.3 NVFP4, Qwen3.8 Flash-Next NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Kimi-K3-INT4, Qwen3.8 27B NVFP4, Motif 3, Nex-N2-Pro, Ternary Bonsai 27B, Nemotron 3.5 Super VL NVFP4, GLM-5.3-MXFP4, K2 Horizon 375B A23B, Qwen3.8 27B MXFP4, Xing4.0-29B-A4B, Nemotron 3.5 Super VL, Solar Open2 250B, Bonsai 27B, A.X-K2, Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, K2-Horizon-32B, Maple-Preview, Intern-S2-Preview (35B-A3B), K-EXAONE 2.0 0803, G9v3-39A5B, Phi-4-reasoning-plus, K2 Horizon 7B, EXAONE 4.5 33B, Nanbeige4.1-3B, HyperNova 60B 2605, Nemotron Cascade 2 30B A3B, INTELLECT-3, Apriel-v1.6-15B-Thinker, K2 Horizon 3.7B, NVIDIA Nemotron-Labs Dory1.0 4B, LFM2.5-24B-A2B, DiffusionGemma 26B A4B, North Mini Code, Falcon-H1R-7B, Ling 3.0 Tiny, MiniCPM5-2B, LongCat Flash Lite, HyperCLOVA X SEED Think (32B), Tri-21B-Think, Olmo 3.1 32B Think, LFM2.5-2.6B, LFM2.5-8B-A1B, Olmo 3.1 32B Instruct, NVIDIA Nemotron 3 Nano 4B, Phi-4-mini-flash-reasoning, Falcon-H1-34B-Instruct, Qwen3.5 2B, Hermes 4 - Llama-3.1 70B, LFM2 24B A2B, Gemma 4 E2B, MiniCPM5-1B, Jamba 1.7 Large, MiniCPM-V 4.6 1.3B, Jamba Reasoning 3B, Tiny Aya Global, Qwen3.5 0.8B, K2 Horizon 0.9B.
66 models with no price data — shown in the strip at the left edge
Muse Wonder Full, Muse Spark Open, Beam 1.0 501B A23B, DeepSeek V4.1 Flash NVFP4, GLM-5.3 Flash NVFP4, GLM-5.3 NVFP4, Qwen3.8 Flash-Next NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Kimi-K3-INT4, Qwen3.8 27B NVFP4, Motif 3, Nex-N2-Pro, Ternary Bonsai 27B, Nemotron 3.5 Super VL NVFP4, GLM-5.3-MXFP4, K2 Horizon 375B A23B, Qwen3.8 27B MXFP4, Xing4.0-29B-A4B, Nemotron 3.5 Super VL, Solar Open2 250B, Bonsai 27B, A.X-K2, Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, K2-Horizon-32B, Maple-Preview, Intern-S2-Preview (35B-A3B), K-EXAONE 2.0 0803, G9v3-39A5B, Phi-4-reasoning-plus, K2 Horizon 7B, EXAONE 4.5 33B, Nanbeige4.1-3B, HyperNova 60B 2605, Nemotron Cascade 2 30B A3B, INTELLECT-3, Apriel-v1.6-15B-Thinker, K2 Horizon 3.7B, NVIDIA Nemotron-Labs Dory1.0 4B, LFM2.5-24B-A2B, DiffusionGemma 26B A4B, North Mini Code, Falcon-H1R-7B, Ling 3.0 Tiny, MiniCPM5-2B, LongCat Flash Lite, HyperCLOVA X SEED Think (32B), Tri-21B-Think, Olmo 3.1 32B Think, LFM2.5-2.6B, LFM2.5-8B-A1B, Olmo 3.1 32B Instruct, NVIDIA Nemotron 3 Nano 4B, Phi-4-mini-flash-reasoning, Falcon-H1-34B-Instruct, Qwen3.5 2B, Hermes 4 - Llama-3.1 70B, LFM2 24B A2B, Gemma 4 E2B, MiniCPM5-1B, Jamba 1.7 Large, MiniCPM-V 4.6 1.3B, Jamba Reasoning 3B, Tiny Aya Global, Qwen3.5 0.8B, K2 Horizon 0.9B
- Best-value frontier (nothing is both cheaper and better)
- Evidencestrong → weak
- Estimated from other categories
- Hover a dot for details · click a lab to highlight it
- Gemini 4 Carbon
- Quality
- 99.7
- Rank
- #1/215
- Price
- $8.00/M tok
- Speed
- 83tok/s
In$4.00▾Out$20▾/M tokvs GPT-6 Astra: +7.0 quality · 0.4× price
- GPT-6 Astra
- Quality
- 92.7
- Rank
- #7/215
- Price
- $20.0/M tok
- Speed
- 52tok/s
In$10Out$50/M tokvs Gemini 4 Carbon: −7.0 quality · 2.5× price
Overview
Quality by category
0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.
Hard reasoning benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.
Benchmarks in other categories (4)· Coding, Writing & chat, Vision, Agents
Coding benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.
Writing & chat benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.
Vision benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.
Agents benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.