Tutorials, deep dives and product notes — built for developers.
OpenAI's cheapest tier cut its price 61%, cut its hallucination rate from 93% to 77%, and lost a point on the independent index. Same-harness data on both generations, where Luna regressed, where it improved, and the ten-week price collapse.
Across all six effort levels, GPT-6 Sol scores within a point of GPT-5.6 Sol and costs about half as much per task. Same-harness data on both, the full effort ladder, where coding improved, where knowledge work regressed, and the November price cliff.
OpenAI shipped GPT-6 Sol 90 minutes after Claude Opus 5.5, at half the token price. Artificial Analysis ran both on the same tests: Sol is cheaper to any index score up to about 44, then runs out of headroom. Every benchmark, both effort ladders and the real bill.
Opus 5.5 matches GPT-6 Astra on Terminal-Bench 4.0 for roughly 40% of the cost per task, with 5x cheaper cache reads. Astra keeps uncontested leads in science, maths and gated offensive security — and OpenAI says it is harder to monitor.
Sixty days apart: a 29.7-point jump on scientific research, a 200,000-line codebase audit that drops from 20+ hours to under 3, and a 40% cost cut — plus four API changes that will 400 your Opus 5 integration.
Opus 5.5 wins eight of the nine benchmarks Anthropic publishes against Fable 5.1 at 2.5x lower token price - but four of those margins sit inside the disclosed error bars. Includes the HAProxy same-task test, the 16-0 research-report result and the one-way thinking-block handoff.
Anthropic's Claude Opus 5.5 matches Fable 5.1 on most work at $4/$20 per million tokens: 66.4% on Terminal-Bench 4.0, 1,846 GDPval-AA Elo, and 40% lower cost per task than Opus 5. Full benchmark table with footnotes, real tester results, the four breaking API changes, and where GPT-6 Astra still wins.
DeepSeek V4.1 Flash wins 5 of the 15 benchmarks it shares with Claude Opus 5 — by an average of 1.94 points, while undercutting it by up to 41.7× on output price. Opus 5's 10 wins average 10.19 points. Full vendor data, community test reports, pricing math, charts and a routing verdict.
Kimi K3 vs GPT-5.6 Sol: Sol leads 6 of 9 shared benchmarks including DeepSWE and Terminal-Bench 2.1. K3 wins FrontierSWE, BrowseComp, and AA-Briefcase at 40% lower cost. Sol Ultra hits 91.9% on Terminal-Bench. Full comparison with radar charts and pricing.
Kimi K3 vs Claude Fable 5 across 35 benchmarks: Fable wins 22, K3 wins 12, 1 tie. K3 leads Terminal-Bench 2.1, SWE Marathon (+7), BrowseComp, and took #1 on the Frontend Code Arena — all at 70% less cost. Fable dominates FrontierSWE (+5.4), HLE (+9.8), and vision. Full scorecard with radar charts and pricing analysis.
Kimi K3 vs Claude Opus 4.8: K3 leads all 9 shared coding benchmarks and costs 40% less. Opus 4.8 counters with independently verified scores, adjustable reasoning, and mature production tooling. Full comparison with radar charts and pricing tables.
GPT-5.6 Luna vs Qwen 3.6 Flash, the Alibaba API alias for Qwen3.6-35B-A3B, compared across official coding, agent, reasoning and vision benchmarks, context, multimodality and pricing.