GPT-5.6 Luna Max vs GPT-6 Sol Max: benchmarks, price and speed

Staying with OpenAI still leaves a decision: GPT-5.6 Luna (Max) or GPT-6 Sol (Max). Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test. The headline gap is on the intelligence index, where GPT-6 Sol Max scores 44.2 and GPT-5.6 Luna Max 23.8.

Benchmark scores

GPT-6 Sol Max comes out ahead on the intelligence index, 44.2 to 23.8. A gap this large suggests the two are built for different jobs. In relative terms, GPT-6 Sol Max scores 86% higher.

For context, that places GPT-5.6 Luna Max 70th and GPT-6 Sol Max 26th out of 109 scored models still on offer.

The catalogue does not yet split either model's score into coding and math indexes.

Running costs

GPT-5.6 Luna Max lists $0.20 per million input tokens and $1.20 per million output tokens; GPT-6 Sol Max lists $2.00 and $10.00. GPT-6 Sol Max costs 8.3 times as much per output token.

Take 1 million input tokens and 200,000 output tokens: that comes to $0.44 on GPT-5.6 Luna Max and $4.00 on GPT-6 Sol Max. A bigger example, a month of coding-assistant traffic at 30 million input and 3 million output tokens, costs $9.60 on GPT-5.6 Luna Max and $90.00 on GPT-6 Sol Max: a gap of $80.40.

Release timing

GPT-5.6 Luna Max came first, on July 9, 2026; GPT-6 Sol Max followed on September 22, 2026.

Is the price in proportion?

A blunt value measure, blended price over intelligence score, puts GPT-5.6 Luna Max at $0.019 and GPT-6 Sol Max at $0.090 per point. GPT-5.6 Luna Max delivers each index point for 79% less; whether GPT-6 Sol Max's extra 20.4 points are worth the premium depends on how often your tasks need them.

Throughput and time to first token

Once a response is under way, GPT-5.6 Luna Max produces roughly 125 tokens per second against 127 tokens per second for GPT-6 Sol Max. Throughput is close to level. The wait for the first token averages 108 seconds on GPT-5.6 Luna Max against 91 seconds on GPT-6 Sol Max. GPT-5.6 Luna Max waits 1.2 times as long before its first token. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

For a 2,000-token response, first token plus generation comes to roughly 2.1 minutes on GPT-5.6 Luna Max and 107 seconds on GPT-6 Sol Max.