Kimi K3 vs Claude Opus 4.8
Kimi K3 is the largest open-weight model ever released at 2.8 trillion parameters. Claude Opus 4.8 is Anthropic's production-hardened flagship. One leads on vendor-reported coding benchmarks and price; the other leads on maturity, controls, and independent verification. This comparison uses Moonshot's official launch table, Anthropic's published scores, and independent leaderboard data to help you pick the right model for real work.
Model cards side by side
| Specification | Kimi K3 | Claude Opus 4.8 |
|---|---|---|
| Provider / release | Moonshot AI · July 16, 2026 | Anthropic · May 28, 2026 |
| API model ID | kimi-k3 | claude-opus-4-8 |
| Architecture | MoE · 2.8T total / 16 of 896 experts active | Proprietary dense (undisclosed) |
| Attention mechanism | Kimi Delta Attention + Attention Residuals | Not publicly detailed |
| Context window | 1,048,576 tokens (1M) | 1M tokens |
| Maximum output | Not stated on launch page | 128K tokens |
| Reasoning modes | Max effort at launch; lower modes planned | Low, Medium, High, Extra, Max + Fast mode (2.5× speed) |
| Input / output | Text and native vision / text | Text and images / text |
| Tools | Function calling, structured outputs | Tool calls, JSON output, MCP, computer use |
| Weights / license | Open weights (Modified MIT), promised by July 27 | Closed, proprietary, API-only |
| Speed option | None announced | Fast mode: 2.5× speed at $10/$50 per 1M |
K3's architectural claim is genuinely unusual: at 2.8 trillion parameters with 16 active experts out of 896, it's the largest open-weight model ever. Its Kimi Delta Attention is a hybrid linear attention mechanism designed to keep long-context inference efficient. Opus 4.8 is a more mature, closed product — Anthropic doesn't disclose its architecture, but the model ships with adjustable reasoning effort, fast mode, and a proven deployment record since late May.
Benchmarks: K3 leads Moonshot's coding table, Opus holds on independent verification
The table below uses Moonshot's official K3 launch comparison, which reports K3 at max effort and Opus 4.8 at max effort. Harnesses differ per benchmark row — Moonshot's footnotes specify which agent scaffold was used for each model. Rows where the harness differs should not be treated as clean head-to-head results.
| Benchmark | Kimi K3 (max) | Opus 4.8 (max) | Interpretation |
|---|---|---|---|
| Terminal-Bench 2.1 | 88.3 | 84.6 | K3 +3.7 · K3 uses KimiCode, Opus uses Terminus 2 |
| FrontierSWE | 81.2 | 66.7 | K3 +14.5 · K3 uses KimiCode; large gap on repo-level engineering |
| DeepSWE | 67.5 | 59.0 | K3 +8.5 · K3 uses KimiCode harness |
| Program Bench | 77.8 | 71.9 | K3 +5.9 · raw pass rate |
| SWE Marathon | 42.0 | 40.0 | K3 +2.0 · both use Claude Code harness; close on sustained autonomy |
| Kimi Code Bench 2.0 | 72.9 | 71.7 | K3 +1.2 · near tie on internal coding-agent eval |
| GDPval-AA v2 (Elo) | 1,668 | 1,600 | K3 +68 Elo · agentic knowledge work |
| PostTrain Bench | 36.6 | 34.1 | K3 +2.5 |
| MLS Bench | 48.3 | 42.8 | K3 +5.5 |
Where Opus 4.8 fights back: Anthropic's own published scores
Anthropic published a different set of benchmarks at Opus 4.8's launch — and on those, Opus shows clear strengths that Moonshot's table doesn't capture:
| Benchmark | Opus 4.8 | Context |
|---|---|---|
| SWE-bench Verified | 88.6% | +1.0 vs Opus 4.7; near ceiling on this benchmark |
| SWE-bench Pro | 69.2% | +4.9 vs Opus 4.7; the harder, less-saturated coding set |
| SWE-bench Multilingual | 84.4% | New for 4.8; strong multilingual code performance |
| MCP-Atlas | 82.2% | +4.9 vs Opus 4.7; tool-calling over MCP |
| BrowseComp (single-agent) | 84.3% | +5.0 vs Opus 4.7 |
| HLE (with tools) | 57.9% | +3.2 vs Opus 4.7 |
| HLE (without tools) | 49.8% | +2.9 vs Opus 4.7 |
| GPQA Diamond | 93.6% | -0.6 vs Opus 4.7; near-saturated, variance expected |
| USAMO 2026 | 96.7% | +27.4 vs Opus 4.7; largest single jump |
| GDPval-AA (Elo) | 1,890 | Clean lead over GPT-5.5 (1,769) and Gemini 3.1 Pro (1,314) |
| GraphWalks BFS 1M | 68.1 | vs 40.3 on Opus 4.7; massive long-context retrieval gain |
Anthropic's GDPval-AA score of 1,890 Elo is notably higher than K3's 1,668 — suggesting Opus still leads on knowledge-work quality. And Opus' 69.2% on SWE-bench Pro (the harder variant) and 88.6% on SWE-bench Verified are independently verified scores that K3 hasn't yet matched in public.
Radar: four shared evidence points
● Kimi K3 ● Opus 4.8
The radar uses four rows where both models have scores in Moonshot's comparison table. Scores are normalized: Term-Bench and FrontierSWE to 100, DeepSWE to 100, GDPval-AA to 2000. It is a visual aid, not a new benchmark.
- K3 leads on all four selected rows in Moonshot's table.
- The gap is widest on FrontierSWE (81.2 vs 66.7) — repository-level engineering.
- GDPval-AA shows a meaningful agentic quality gap in K3's favor within this table, though Anthropic's own GDPval-AA score for Opus 4.8 is 1,890.
- Opus 4.8's advantages lie outside this polygon: adjustable effort, fast mode, mature tooling, independent verification, and SWE-bench Pro leadership.
Independent verification: what the public leaderboards show
| Leaderboard | Kimi K3 | Claude Opus 4.8 | Notes |
|---|---|---|---|
| Artificial Analysis Intelligence Index | ~57 | ~56 | K3 edges ahead; both behind Fable 5 (~60) and GPT-5.6 Sol (~59) |
| Terminal-Bench 2.1 (public) | Not listed | 78.9% (Claude Code, #5) | K3's 88.3% uses KimiCode harness, not yet on public board |
| MCP-Atlas (public) | Not listed | 82.2% (#3) | K3 not yet on BenchLM MCP Atlas leaderboard |
| SWE-bench Verified (public) | Not listed | 88.6% (#3) | K3 not yet on public SWE-bench leaderboards |
| Frontend Code Arena | #1 | Not in top ranks | K3 jumped 17 places from K2.6's #18; leads 6 of 7 domains |
| GPQA Diamond (open-weight) | 93.5% | 93.6% (closed) | K3: strongest open-weight GPQA result at launch |
The independent picture is mixed. K3 leads the Frontend Code Arena and posts the best open-weight GPQA Diamond score. But on established public leaderboards — Terminal-Bench, MCP-Atlas, SWE-bench — Opus 4.8 has verified, traceable scores while K3 has not yet appeared. This doesn't mean K3's scores are wrong; it means they haven't been independently reproduced yet.
Pricing: K3 costs 40% less at list price
| Per 1M tokens | Kimi K3 | Claude Opus 4.8 |
|---|---|---|
| Fresh input / cache miss | $3.00 | $5.00 |
| Cached input / cache hit | $0.30 | $0.50 |
| Output | $15.00 | $25.00 |
| 10M fresh input + 1M output | $45.00 | $75.00 |
| 10M cached input + 1M output | $18.00 | $30.00 |
K3 is cheaper on every token class. But there's a catch: K3 always runs at max reasoning effort, which means reasoning tokens are billed as output at $15/M. Opus lets you dial effort down (or up) and offers fast mode at $10/$50 for latency-sensitive work. The real cost comparison is cost per accepted task, not cost per token — if Opus succeeds in one shot while K3 needs three, the rate card advantage evaporates.
Artificial Analysis measured per-task cost: K3 at $0.94, Opus 4.8 at $1.80, and GPT-5.6 Sol at $1.04. K3's token efficiency (fewer tokens per correct answer) partially offsets its higher per-token price versus its predecessor K2.6.
Open weights: the strategic advantage (with practical caveats)
K3: open weights by July 27
Moonshot has committed to releasing full weights under a Modified MIT license by July 27, 2026. At 2.8T parameters with 16 active experts, self-hosting requires serious infrastructure — Moonshot recommends at least 64 accelerators. Most teams will use an inference provider.
The MIT license enables fine-tuning, air-gapped deployment, auditability, and sovereignty that closed models cannot match. For regulated industries or organizations that cannot send data to external APIs, this is a decisive advantage.
Opus 4.8: API-only, but battle-tested
Opus 4.8 is closed and API-only — no weights, no self-hosting, no fine-tuning. What you get instead: mature SDK support across every major language, prompt caching, adjustable effort controls, fast mode, computer use, and a production record spanning nearly two months.
Anthropic's tooling ecosystem (Claude Code, MCP, dynamic workflows with parallel sub-agents) is tightly integrated with Opus. For teams that want a managed, reliable API without infrastructure headaches, this is the pragmatic choice.
Which model should you use?
Choose Kimi K3 if…
- You need the strongest open-weight model available and can wait for weights (or use the API now).
- Your primary workload is frontend coding — K3 is #1 on the Frontend Code Arena.
- API cost is a first-order constraint and you can validate K3's output quality on your tasks.
- You need air-gapped deployment, fine-tuning, or data sovereignty that closed APIs cannot provide.
- You want to run high-volume, measurable coding tasks with clear pass/fail criteria.
Choose Claude Opus 4.8 if…
- You need a proven, independently verified model with public leaderboard traces.
- Your workflow benefits from adjustable reasoning effort — dial up for hard problems, down for routine ones.
- You rely on Anthropic's tooling: Claude Code, MCP, computer use, dynamic workflows with parallel sub-agents.
- Judgment, recovery from errors, and production reliability matter more than raw benchmark scores.
- You want fast mode (2.5× speed) for latency-sensitive applications.
Compare both models on real code
Run the same repository prompt, tool schema, and acceptance tests rather than trusting a leaderboard headline.
Try both in CodingFleet →Final verdict
Kimi K3 wins the benchmark headline contest. On Moonshot's launch table, it leads every coding row against Opus 4.8, sometimes by wide margins. It's #1 on the Frontend Code Arena, posts the strongest open-weight GPQA Diamond score, and costs 40% less at list price. For teams that can validate its output on their own tasks, it's an extraordinarily compelling option — especially once the weights land.
Claude Opus 4.8 wins the operational maturity contest. Its scores are independently verified on public leaderboards. It offers adjustable reasoning effort, a 2.5× fast mode, mature SDK support, and nearly two months of production hardening. On SWE-bench Pro (69.2%), MCP-Atlas (82.2%), and GDPval-AA (1,890 Elo), it posts strong, traceable results that K3 hasn't yet matched in public.
The honest assessment: K3 is the most exciting open-weight release of 2026 and a genuine threat to closed-model dominance. But "exciting" and "production-ready" are different standards. Test both on your actual workload. The model that finishes your work with the least total friction is the right one.
Sources and methodology
- Moonshot AI — Kimi K3 Tech Blog. Official launch table, architecture, and benchmark scores.
- Anthropic — Claude Opus 4.8 system card. Official benchmark scores, pricing, and features.
- Terminal-Bench 2.1 public leaderboard. Independent, traceable scores with harness details.
- BenchLM — Claude Opus 4.8. Aggregated independent benchmark scores.
- BenchLM — MCP Atlas leaderboard. Public MCP tool-calling benchmark.
- Codersera — Kimi K3 Benchmarks. Independent analysis including Artificial Analysis Intelligence Index scores.
- AIHubMix — Kimi K3 pricing and eesel — K3 pricing analysis.
- LLM Stats — Opus 4.8 launch analysis. Detailed benchmark deltas vs Opus 4.7.
- All benchmark rows retain their source labels and harness details. Provider-reported results can differ because of harness, prompt, context, and reasoning-budget choices. The radar and bar charts are visual aids, not statistically normalized leaderboards.