2026 Mainstream Foundation Models Comparison: GPT-5.4 vs Claude Opus 4.6 vs Gemini 3.1 Pro

Posted on Oct 21 • Originally published at blog.llmgo.top

This comparison preserves the GPT-5.4, Claude Opus / Sonnet 4.6, and Gemini 3.1 Pro group. It is an engineering reference, not a claim that these are today's newest models. Specifications come from provider documentation; unsupported score tables are not treated as controlled measurements. See the Chinese open-weight comparison.

Sources: GPT-5.4, Opus 4.6, Sonnet 4.6, Gemini 3.1 Pro Preview.

ChatGPT's Thinking label is not a separate gpt-5.4-thinking API ID. Claude Code Agent Teams is a harness capability rather than automatic multi-agent orchestration in the base API. Distinguish API thinking parameters from separate consumer product modes.

Standard examples below are USD per million tokens. Account separately for long-context rates, cache writes, batch processing, regions, and tools.

Sources: OpenAI model pricing, Claude model documentation, Gemini pricing. GPT-5.4 applies long-context multipliers above 272K input tokens, so the standard rate cannot be applied to every million-token request.

SWE-bench Verified, HumanEval, OSWorld, and mathematics tests measure different capabilities. Do not place Opus results in a Sonnet column or describe provider-specific harness results as one uniform reproduction.

Pin the snapshot, reasoning budget, context, tool permissions, agent harness, timeout, and retries. Save patches, execution logs, and independent acceptance results. Compare quality, latency, and useful cost; see LLM evaluation.

A large window does not establish complete repository understanding. A reported hallucination reduction on one evaluation is not a fixed improvement for all workloads.

These examples require provider SDKs, credentials, and account access. Site verification does not call external models.

from openai import OpenAI client = OpenAI () response = client. responses. create ( model = " gpt-5.4 ", input = " Explain the basics of quantum computing ", reasoning = { " effort ": " high " }, max_output_tokens = 4096, ) print ( response. output_text ) Enter fullscreen mode Exit fullscreen mode import anthropic client = anthropic. Anthropic () response = client. messages. create ( model = " claude-sonnet-4-6 ", max_tokens = 4096, messages = [{ " role ": " user ", " content ": " Explain quantum computing " }], ) print ( response. content ) Enter fullscreen mode Exit fullscreen mode from google import genai client = genai. Client () response = client. models. generate_content ( model = " gemini-3.1-pro-preview ", contents = " Explain quantum computing ", ) print ( response. text ) Enter fullscreen mode Exit fullscreen mode Check IDs against your account's model list.

Provider routing also needs consistent errors, deadlines, tool schemas, and usage accounting.

At an assumed $30/hour server cost and blended $5 per million API tokens, a simplified break-even point is 30 / 5 × 1e6 / 3600 = 1,667 tokens/s. This is not measured capacity or equivalent task quality. Input / output mix, utilization, expansion, and staffing change the result. See deployment cost estimation.

For ordinary GQA with 80 layers, 8 KV heads, head_dim=128, and FP16, cache bytes per token are 2×80×8×128×2=327,680. One million tokens require about 327.68GB or 305.18GiB. This is a defined example, not a rule for all 70B or hybrid models. PagedAttention improves allocation and reuse, not the size of an uncompressed KV element.

Compare matching repository tasks, tools, and budgets. Provider benchmarks screen candidates; independent acceptance determines fit.

No. Capacity, retrieval quality, citation reliability, and cost need separate measurements.

Set minimum quality and SLA first, then compare useful cost. The token calculator helps separate input, output, and cache charges.

Originally published at LLM Systems Architecture on blog.llmgo.top.