Skip to content

The frontier

As of October 25, 2026, the highest Analyzer Index on the price frontier is Claude Opus 5.5 at 98.4, with a blended price of $8.00 per million tokens. A model is on the frontier when no other model beats it on both capability and price.

Every dot is a model. The line joins models that no other model beats on both axes at once. Change the axes to trade capability against price, speed, latency or context; the URL keeps your view so you can share it. Capability is the Analyzer Index v1.0.

Where the frontier splits

Rank on each scenario for the models on this chart. A column’s #1 is the leaderboard leader. The middle card picks the highest quality score on each scenario among models with coverage close to the all-rounder’s, so a score from one slice of the benchmarks cannot win. Both figures are a benchmark-level estimate: one published score per scenario, with no live agent trace.

One model for every scenario

Gemini 4 Argon

Average quality 80.2 across 8 scenarios. Equal-weight monthly cost $458.91.

Highest quality on each scenario

6 models

Average quality 98.6, 18.4 points above Gemini 4 Argon. That mix averages $565.78 per month, about 23% more than Gemini 4 Argon.

Each scenario’s current leader

8 models

Average quality 95.9, 15.6 points above Gemini 4 Argon. These ranks already include each scenario’s cost weight. That mix averages $203.13 per month, about 56% less than Gemini 4 Argon.

Traffic mix

Each scenario has an equal share. Move a slider to weight the monthly cost.

Scenario ranks for models that lead at least one scenario. Rank 1 matches the current leaderboard leader for that scenario.
Model👨‍💻 Coding Assistant💬 Customer Support Bot🔬 Research / Analyst🧮 Math / Reasoning Tutor🏷️ Bulk Classification📊 Data / BI Analyst⚡ Realtime Chat / Voice🛡️ Production Critical
Gemini 4 ArgonBest singleGoogle1, rank 1 on Coding Assistant5, rank 5 on Customer Support Bot3, rank 3 on Research / Analyst3, rank 3 on Math / Reasoning Tutor45, rank 45 on Bulk Classification179, rank 179 on Data / BI Analyst55, rank 55 on Realtime Chat / Voice52, rank 52 on Production Critical
GPT-6 AstraOpenAI20, rank 20 on Coding Assistant127, rank 127 on Customer Support Bot2, rank 2 on Research / Analyst5, rank 5 on Math / Reasoning Tutor159, rank 159 on Bulk Classification248, rank 248 on Data / BI Analyst200, rank 200 on Realtime Chat / Voice68, rank 68 on Production Critical
Claude Opus 5.5Anthropic3, rank 3 on Coding Assistant64, rank 64 on Customer Support Bot4, rank 4 on Research / Analyst4, rank 4 on Math / Reasoning Tutor114, rank 114 on Bulk Classification242, rank 242 on Data / BI Analyst145, rank 145 on Realtime Chat / Voice51, rank 51 on Production Critical
Claude Sonnet 4 (Thinking)Anthropic141, rank 141 on Coding Assistant153, rank 153 on Customer Support Bot254, rank 254 on Research / Analyst257, rank 257 on Math / Reasoning Tutor185, rank 185 on Bulk Classification4, rank 4 on Data / BI Analyst226, rank 226 on Realtime Chat / Voice257, rank 257 on Production Critical
GPT-5.6 Terra ProOpenAI240, rank 240 on Coding Assistant230, rank 230 on Customer Support Bot233, rank 233 on Research / Analyst237, rank 237 on Math / Reasoning Tutor226, rank 226 on Bulk Classification185, rank 185 on Data / BI Analyst1, rank 1 on Realtime Chat / Voice39, rank 39 on Production Critical
GPT-5.6 SolOpenAI18, rank 18 on Coding Assistant35, rank 35 on Customer Support Bot5, rank 5 on Research / Analyst11, rank 11 on Math / Reasoning Tutor118, rank 118 on Bulk Classification225, rank 225 on Data / BI Analyst164, rank 164 on Realtime Chat / Voice47, rank 47 on Production Critical
DeepSeek V4.1 FlashDeepSeek15, rank 15 on Coding Assistant6, rank 6 on Customer Support Bot34, rank 34 on Research / Analyst20, rank 20 on Math / Reasoning Tutor1, rank 1 on Bulk Classification44, rank 44 on Data / BI Analyst9, rank 9 on Realtime Chat / Voice99, rank 99 on Production Critical
Gemini 3.8 FlashGoogle4, rank 4 on Coding Assistant1, rank 1 on Customer Support Bot13, rank 13 on Research / Analyst19, rank 19 on Math / Reasoning Tutor21, rank 21 on Bulk Classification141, rank 141 on Data / BI Analyst26, rank 26 on Realtime Chat / Voice61, rank 61 on Production Critical
Gemini 2.0 FlashGoogle155, rank 155 on Coding Assistant57, rank 57 on Customer Support Bot78, rank 78 on Research / Analyst126, rank 126 on Math / Reasoning Tutor42, rank 42 on Bulk Classification1, rank 1 on Data / BI Analyst47, rank 47 on Realtime Chat / Voice145, rank 145 on Production Critical
Nemotron 3.5 LightningNVIDIA145, rank 145 on Coding Assistant105, rank 105 on Customer Support Bot150, rank 150 on Research / Analyst155, rank 155 on Math / Reasoning Tutor39, rank 39 on Bulk Classification47, rank 47 on Data / BI Analyst41, rank 41 on Realtime Chat / Voice1, rank 1 on Production Critical
GPT-6.1 SolOpenAI65, rank 65 on Coding Assistant147, rank 147 on Customer Support Bot1, rank 1 on Research / Analyst2, rank 2 on Math / Reasoning Tutor102, rank 102 on Bulk Classification181, rank 181 on Data / BI Analyst119, rank 119 on Realtime Chat / Voice182, rank 182 on Production Critical
DeepSeek V4.1 Flash 1017DeepSeek201, rank 201 on Coding Assistant185, rank 185 on Customer Support Bot87, rank 87 on Research / Analyst1, rank 1 on Math / Reasoning Tutor168, rank 168 on Bulk Classification85, rank 85 on Data / BI Analyst242, rank 242 on Realtime Chat / Voice219, rank 219 on Production Critical
  • Rank 1
  • Top 3
  • Top 10

This table is the shared model pool. Local / Self-Hosted Coding ranks a narrower set.

On the price frontier today

Models on the Pareto frontier, highest score first
ModelIndexBlended $/M
Claude Opus 5.5Anthropic98.4$8.000
Gemini 4 ArgonGoogle98.3$2.000
Gemini 3.7 FlashGoogle88.7$0.750
DeepSeek V3 (Thinking)DeepSeek82.0$0.503
GLM 5.3 FlashZhipu AI (GLM)80.4$0.238
GPT-5.6 LunaOpenAI75.2$0.225
GPT-6 LunaOpenAI72.5$0.100
GPT-5 nanoOpenAI35.4$0.069
gpt-oss-20bOpenAI35.2$0.036

Trends over time

Frontier by scenario

👨‍💻 Coding Assistant🖥️ Local / Self-Hosted Coding💬 Customer Support Bot🔬 Research / Analyst🧮 Math / Reasoning Tutor🏷️ Bulk Classification📄 Multimodal Document Q&A📊 Data / BI Analyst⚡ Realtime Chat / Voice🛡️ Production Critical